JevCode / Ecosystem

Jev coverage

571 projects, each naming the specific decision Jev makes with an evidence link you can open. Verification labels describe evidence, not a score.

Reviewed: 2026-10-29

Official

TypeSafe agent skills
Packages Jev primitives, patterns and evaluation habits into agent-loadable skills so a coding agent fixes the answer type before writing the call.
Evidencehttps://github.com/typesafe-ai/skills
Labelspublic-sourcemaintainer-runbook
System One adapter (Python)
Swaps the underlying LLM behind one client interface to compare Jev against chat models on decision quality, without touching client code.
Evidencehttps://github.com/typesafe-ai/system-one-adapter-python
Labelspublic-sourcemaintainer-runbook

SDKs & clients

TypeSafe JavaScript SDK
Narrows a call result to the declared answer type on the TypeScript side, so the decision outcome needs no runtime parsing.
Evidencehttps://github.com/typesafe-ai/typesafe-sdk-js
Labelspublic-sourcemaintainer-runbook
laya-php
Maps Jev-compatible typed decisions into native PHP types and takes over the decision points inside Laravel.
Evidencehttps://github.com/marcreichel/laya-php/blob/main/src/Laya.php#L197
Labelspublic-sourcecall-site-verified
go-jev
A Go client that wraps Jev typed answers as a library and ships jev-cli for direct use in UNIX pipelines.
Evidencehttps://github.com/mattn/go-jev/blob/main/jev.go#L19
Labelspublic-sourcemaintainer-runbookcall-site-verified
zio-typesafe-ai
A Scala 3 / ZIO library that types the Jev System One API end-to-end, so callers never handle raw JSON.
Evidencehttps://github.com/jamesward/zio-typesafe-ai/blob/main/src/main/scala/com/jamesward/zio_typesafe_ai/TypeSafeAI.scala#L3
Labelspublic-sourcecall-site-verified
jev-java
An idiomatic Java 17+ client library for the Jev System One decision engine.
Evidencehttps://github.com/Olti1947/jev-java/blob/main/src/main/java/io/github/Olti1947/jev/JevClient.java#L137
Labelspublic-sourcecall-site-verified
jev-sdk-java
A small type-safe Java 21 client for the TypeSafe AI Jev decision API.
Evidencehttps://github.com/luigivis/jev-sdk-java/blob/main/src/main/java/com/luigivismara/jev/JevClient.java#L156
Labelspublic-sourcecall-site-verified
typesafe-sdk (Rust)
A Rust client that ships a blocking feature alongside the default async usage.
Evidencehttps://github.com/codeitlikemiley/typesafe-sdk-rust/blob/main/benches/client_overhead.rs#L15
Labelspublic-sourcemaintainer-runbookcall-site-verified
kunobi-jev
A Rust client for typed decision models that covers Jev alongside other hosted providers behind one typed call.
Evidencehttps://github.com/kunobi-ninja/kunobi-jev/blob/main/src/blocking.rs#L27
Labelspublic-sourcecall-site-verified
tinyjevclient
A compact typed Rust client scoped to the System One API call surface.
Evidencehttps://github.com/tinyhumansai/tinyjevclient/blob/main/README.md#L3
Labelspublic-sourcereadme-claim
typesafe.zig
Zig bindings ask typed Choice, Noul and Score questions about application state in one call.
Evidencehttps://github.com/mattneel/typesafe.zig/blob/master/src/Client.zig#L353
Labelspublic-sourcecall-site-verified
openai-scala-client
A general LLM client that treats decision models as a peer API class, placing Jev System One alongside OpenAI Decisions.
Evidencehttps://github.com/cequence-io/openai-scala-client/blob/master/typesafe-client/src/main/scala/io/cequence/openaiscala/typesafe/JsonFormats.scala#L125
Labelspublic-sourcecall-site-verified
decisionkit-dotnet
A provider-independent .NET decision engine with Jev support as one of its backends.
Evidencehttps://github.com/iamjonatha/decisionkit-dotnet/blob/main/README.md#L3
Labelspublic-sourcereadme-claim
typesafeai-dotnet-sdk
A community-maintained, explicitly independent .NET client for the System One HTTP API.
Evidencehttps://github.com/saibimajdi/typesafeai-dotnet-sdk/blob/main/src/TypeSafe.Sdk/ITypeSafeClient.cs#L34
Labelspublic-sourcecall-site-verified
Bodila51/grok-bot-jev
README states: A Python router around the TypeSafe SDK's system_one call.
Evidencehttps://github.com/Bodila51/grok-bot-jev/blob/main/jevopus/jevopus.py#L22
Labelscall-site-verified
boozedog/pi-codemode
README states: When a TypeSafe API key is present, Codemode injects guest jev.ask into QuickJS and the type checker. Without a key, Codemode is unchanged: no jev global, no HTTP, and no @typesafe-ai/sdk dependency.
Evidencehttps://github.com/boozedog/pi-codemode/blob/master/src/jev/client.ts#L5
Labelscall-site-verified
chaitin/Decis
README states: official typesafe-sdk already speaks — so pointing the SDK at your own host is the whole
Evidencehttps://github.com/chaitin/Decis/blob/master/playground/__init__.py#L3
Labelscall-site-verified
codeitlikemiley/typesafe-sdk-rust
README states: typesafe-sdk = { version = "0.3", features = ["blocking"] }
Evidencehttps://github.com/codeitlikemiley/typesafe-sdk-rust/blob/main/benches/client_overhead.rs#L15
Labelscall-site-verified
dakdevs/decide-mcp
README states: Defaults to TypeSafe AI Jev through AI Gateway, using AI SDK 7's experimental_evaluate. Supports custom decision policies, multiple bias profiles, automatic profile routing, and individual tools per profile.
Evidencehttps://github.com/dakdevs/decide-mcp/blob/main/src/providers.ts#L5
Labelscall-site-verified
deepanwadhwa/OpenDecision
README states: A Python API, a FastAPI server, and a TypeSafe SDK compatible endpoint.
Evidencehttps://github.com/deepanwadhwa/OpenDecision/blob/main/demos/images/measure_latency.py#L79
Labelscall-site-verified
emrickgarrett/OneVOneJev
README states: AI: @typesafe-ai/sdk (jev-latest) with heuristic fallback
Evidencehttps://github.com/emrickgarrett/OneVOneJev/blob/main/server/src/jev.ts#L7
Labelscall-site-verified
iapp-technology/openthai-systemone
README states: mirrors TypeSafe AI's POST /v1/systemone (Jev), so SDK code written for TypeSafe can point at this model.
Evidencehttps://github.com/iapp-technology/openthai-systemone/blob/main/demo/doom_demo.py#L25
Labelscall-site-verified
InsaneArts/typesafe-sdk-swift
README states: package(url: "https://github.com/InsaneArts/typesafe-sdk-swift", from: "0.2.0")
Evidencehttps://github.com/InsaneArts/typesafe-sdk-swift/blob/main/README.md#L10
Labelsreadme-claim
kunobi-ninja/kunobi-jev
README states: Rust client for typed decision models: TypeSafe Jev, Cloudflare Clef, Liquid d1,
Evidencehttps://github.com/kunobi-ninja/kunobi-jev/blob/main/src/blocking.rs#L27
Labelscall-site-verified
lambertsj/beatjev
README states: It's a Cloudflare Worker. public/ is served as static assets (plain HTML/CSS/JS, no build step). src/worker.js handles POST /api/classify and calls Jev through @typesafe-ai/sdk, so the API key stays server-side.
Evidencehttps://github.com/lambertsj/beatjev/blob/main/src/worker.js#L6
Labelscall-site-verified
logan-markewich/jeff
README states: Use the official typesafe-sdk by pointing TYPESAFE_BASE_URL at jeff.
Evidencehttps://github.com/logan-markewich/jeff/blob/main/bench/eval_accuracy.py#L70
Labelscall-site-verified
luigivis/jev-sdk-java
README states: A small, type-safe Java 21 client for the TypeSafe AI Jev (System One) decision API.
Evidencehttps://github.com/luigivis/jev-sdk-java/blob/main/src/main/java/com/luigivismara/jev/JevClient.java#L156
Labelscall-site-verified
MoLeMo-Lab/mojev
README states: wire-compatible with the TypeSafe Python SDK's system_one API.
Evidencehttps://github.com/MoLeMo-Lab/mojev/blob/master/mojev/apitest.py#L48
Labelscall-site-verified
nshkrdotcom/typesafe_sdk
README states: The TypeSafe-specific provider/API SDK. It owns TypeSafe authentication,
Evidencehttps://github.com/nshkrdotcom/typesafe_sdk/blob/main/codegen/typesafe_sdk/codegen/source/openapi.ex#L20
Labelscall-site-verified
Olti1947/jev-java
README states: Idiomatic Java 17+ client library for TypeSafe AI's Jev System One decision engine.
Evidencehttps://github.com/Olti1947/jev-java/blob/main/src/main/java/io/github/Olti1947/jev/JevClient.java#L137
Labelscall-site-verified
Premo-Cloud/typesafe-sdk-java
README states: implementation("io.github.premo-cloud:typesafe-sdk:0.6.0")
Evidencehttps://github.com/Premo-Cloud/typesafe-sdk-java/blob/main/typesafe-sdk/src/main/java/io/github/premocloud/typesafe/TypeSafeClient.java#L54
Labelscall-site-verified
saibimajdi/typesafeai-dotnet-sdk
README states: This is a community SDK. It is an independent client for the TypeSafe AI System One HTTP API,
Evidencehttps://github.com/saibimajdi/typesafeai-dotnet-sdk/blob/main/src/TypeSafe.Sdk/ITypeSafeClient.cs#L34
Labelscall-site-verified
ticofab/scala-jev-sdk
README states: libraryDependencies += "io.github.ticofab" %% "scala-jev-sdk" % " "
Evidencehttps://github.com/ticofab/scala-jev-sdk/blob/master/README.md#L14
Labelsreadme-claim
tinyhumansai/tinyjevclient
README states: tinyjevclient is a typed Rust client for TypeSafe AI's System One API and
Evidencehttps://github.com/tinyhumansai/tinyjevclient/blob/main/README.md#L3
Labelsreadme-claim
vicfei/awesome-jev-prompts
README states: import { choice, noul, score, TypeSafeClient } from "@typesafe-ai/sdk";
Evidencehttps://github.com/vicfei/awesome-jev-prompts/blob/main/README.md#L96
Labelsreadme-claim

Jev-like models

ollaya
Implements a Jev-shaped decision service in Rust so a backend can get typed answers without depending on the hosted model.
Evidencehttps://github.com/ollaya-dev/ollaya/blob/main/crates/ollaya-server/src/http.rs
Labelspublic-sourcecall-site-verified
JevAny
Reproduces the Jev decision interface at the model layer for environments that cannot reach the hosted service directly.
Evidencehttps://github.com/weitianxin/JevAny/blob/main/jevany/model.py
Labelspublic-sourcecall-site-verified
eikos
Pulls the decision step out of the generation chain and lets a typed model return the conclusion on its own.
Evidencehttps://github.com/caiovicentino/eikos/blob/main/eikos/serve.py#L343
Labelspublic-sourcecall-site-verified
abhishek085/open-spark-jev
README states: An open-source, local implementation inspired by TypeSafe's Jev and System One models, built for NVIDIA DGX Spark. The model is called spark-s1 .
Evidencehttps://github.com/abhishek085/open-spark-jev/blob/main/open_spark_jev/experimental/control_es.py#L11
Labelscall-site-verified
alvarobartt/sys1
README states: Blazing fast structured decisions for System One open-models self-hosted with a TypeSafe AI compatible API, written in Rust.
Evidencehttps://github.com/alvarobartt/sys1/blob/main/benchmark.py#L791
Labelscall-site-verified
DECRUX9812/openjev
README states: An open, local, zero-cost reimplementation of the Jev decision layer for job postings.
Evidencehttps://github.com/DECRUX9812/openjev/blob/main/README.md#L3
Labelsreadme-claim

Frameworks & integrations

DeciFlow
Orchestrates flow with typed decision nodes, where branch conditions are decided directly by the enum value Jev returns.
Evidencehttps://github.com/call518/DeciFlow
Labelspublic-sourcedemo-only
jev4pg
Pushes textual predicates down to Jev inside PostgreSQL while keeping probabilities and source evidence; exact joins and aggregates stay in SQL.
Evidencehttps://github.com/Sheltercosmo/jev4pg/blob/main/sdd/evaluators.py#L39
Labelspublic-sourcecall-site-verified
Gut Check
Jev scores Home Assistant entity health and upgrade risk, and blocks automatic changes whenever confidence is low.
Evidencehttps://github.com/funkadelic/ha-gutcheck/blob/main/custom_components/gutcheck/budget.py#L23
Labelspublic-sourcecall-site-verified
zod-jev
One parseAsync call sends an entire Zod schema ruleset to Jev as a single request, then turns the probabilities into Zod issues while callers keep using native Zod APIs.
Evidencehttps://github.com/jomatsu/zod-jev/blob/main/scripts/check-package.mjs#L35
Labelspublic-sourcecall-site-verified
spring-ai-typesafe
Implements the Jev API on Spring RestClient and Jackson 3, plus Spring AI integrations.
Evidencehttps://github.com/spring-ai-community/spring-ai-typesafe/blob/main/typesafe-java-sdk/src/main/java/org/springaicommunity/typesafe/TypeSafeClient.java#L47
Labelspublic-sourcecall-site-verified
GenieRobot/typesafe-ai-rails
README states: Community Rails integration for TypeSafe AI's System One API, built on the
Evidencehttps://github.com/GenieRobot/typesafe-ai-rails/blob/main/lib/typesafe/rails/client.rb#L55
Labelscall-site-verified
irzix/nestjs-agentic
README states: | @nestjs-agentic/jev | Jev (TypeSafe System One) action gates, output rails, and evaluation judges |
Evidencehttps://github.com/irzix/nestjs-agentic/blob/main/README.md#L70
Labelsreadme-claim
liuhongrui087-art/jev-routed-agent
README states: A multi-step reasoning agent built with LangChain v1 + Jev + Flask + Ollama.
Evidencehttps://github.com/liuhongrui087-art/jev-routed-agent/blob/master/services/router.py#L22
Labelscall-site-verified
Para-FR/casse-brique-typesafe
README states: A brick breaker you can play in the browser, built with Next.js 16, React 19, TypeScript and Tailwind CSS 4. The paddle can be handed over to an AI pilot powered by TypeSafe AI's Jev model.
Evidencehttps://github.com/Para-FR/casse-brique-typesafe/blob/main/src/app/api/paddle/route.ts#L108
Labelscall-site-verified
spring-ai-community/spring-ai-typesafe
README states: API (jev), built on Spring RestClient and Jackson 3, plus Spring AI integrations that
Evidencehttps://github.com/spring-ai-community/spring-ai-typesafe/blob/main/typesafe-java-sdk/src/main/java/org/springaicommunity/typesafe/TypeSafeClient.java#L47
Labelscall-site-verified

Agent tooling

jev-cli
A thin CLI wrapper over the System One API: JSON in, typed decisions out, with no extra abstraction.
Evidencehttps://github.com/lhotwll217/jev-cli/blob/main/src/client.ts#L25
Labelspublic-sourcecall-site-verified
pi-typesafe
Hands small structured judgments such as classify, triage, compare and score to Jev, returning calibrated numbers to the agent in one batched call.
Evidencehttps://github.com/DevMortimer/pi-typesafe/blob/main/src/ask.ts#L32
Labelspublic-sourcecall-site-verified
agent-reflex
A guard plugin for coding agents that routes dangerous shell commands to a swappable decision model, Jev included.
Evidencehttps://github.com/psygreg/agent-reflex/blob/main/plugins/hermes/classifier.py#L34
Labelspublic-sourcecall-site-verified
APUS-AI-Lab/fast-browser-use
README states: Open-Source Reverse Engineering of Jev · Pure Local Browser-Use Agent Skill
Evidencehttps://github.com/APUS-AI-Lab/fast-browser-use/blob/main/README.md#L29
Labelsreadme-claim
BeLazy167/typesafe-mod
README states: A Claude Code function hook that sends two kinds of decision to TypeSafe's Jev
Evidencehttps://github.com/BeLazy167/typesafe-mod/blob/main/hooks/suggest.ts#L27
Labelscall-site-verified
dbreunig/building-with-jev-skill
README states: This repo holds an agent skill for writing and improving programs that call Jev, TypeSafe's System One model.
Evidencehttps://github.com/dbreunig/building-with-jev-skill/blob/main/README.md#L3
Labelsreadme-claim
EliaAlberti/jev-rules
README states: claude plugin update jev-rules@jev-rules
Evidencehttps://github.com/EliaAlberti/jev-rules/blob/main/README.md#L62
Labelsreadme-claim
geilt/typesafe-cli
README states: Small Python CLI + agent skill for TypeSafe System One (Jev).
Evidencehttps://github.com/geilt/typesafe-cli/blob/main/README.md#L3
Labelsreadme-claim
getexcited/stepwarden
README states: It is built on two early-access dependencies (Claude Code function hooks and Jev),
Evidencehttps://github.com/getexcited/stepwarden/blob/main/lib/jev.ts#L30
Labelscall-site-verified
HyunjunJeon/pi-quiet-ask
README states: TypeSafe Jev as the pi coding agent's quiet decision layer.
Evidencehttps://github.com/HyunjunJeon/pi-quiet-ask/blob/main/bench/src/jev_bench/providers/jev.py#L12
Labelscall-site-verified
iamjonatha/jev-book-tags
README states: JEV Book Tags is a calibre plugin that uses TypeSafe AI JEV to suggest subject and genre tags for books in a calibre library. It preserves existing tags and lets you review suggestions before applying them.
Evidencehttps://github.com/iamjonatha/jev-book-tags/blob/main/plugin/client.py#L7
Labelscall-site-verified
jbt95/jev-toolkit
README states: A small stdio MCP server for TypeSafe/Jev with three tools: typesafe_ask for
Evidencehttps://github.com/jbt95/jev-toolkit/blob/main/src/core/paths.ts#L13
Labelscall-site-verified
Jhonnyr97/JevGuard
README states: Then run /plugin configure jevguard@jevguard to set the Jev API key and
Evidencehttps://github.com/Jhonnyr97/JevGuard/blob/master/README.md#L19
Labelsreadme-claim
KamilPostrozny/pi-jev-code
README states: Single-agent Jev coprocessor for Pi coding sessions. Your normal Pi model remains the only coding agent; there are no planners, subagents, reviewers, task graphs, or orchestration.
Evidencehttps://github.com/KamilPostrozny/pi-jev-code/blob/main/src/index.ts#L6
Labelscall-site-verified
kbhuw/jev-sift
README states: Get a key from the TypeSafe dashboard and provide it as JEV_API_KEY in the MCP server's environment. TYPESAFE_API_KEY also works.
Evidencehttps://github.com/kbhuw/jev-sift/blob/main/README.md#L11
Labelsreadme-claim
King4s/Jev-AI-Skill
README states: Jev-AI-Skill is one skill and one MCP server for Claude Code, Codex and Hermes. Jev,
Evidencehttps://github.com/King4s/Jev-AI-Skill/blob/main/README.md#L10
Labelsreadme-claim
KorenKrita/cliproxy-embeddings-rerank-forward
README states: A native plugin for CLIProxyAPI that forwards OpenAI-compatible /v1/embeddings, Cohere-style rerank, and Jev decision requests (OpenRouter Decisions API and TypeSafe System One API) to upstream providers. Supports multip
Evidencehttps://github.com/KorenKrita/cliproxy-embeddings-rerank-forward/blob/main/README.md#L3
Labelsreadme-claim
leepokai/jev-guard
README states: jev-guard key writes ~/.jev-guard/config.json (mode 0600). Every adapter reads that file, so it works for GUI hosts that never see your shell profile. Environment variables win when present: JEV_API_KEY, AI_GATEWAY_API_K
Evidencehttps://github.com/leepokai/jev-guard/blob/main/README.md#L73
Labelsreadme-claim
leonaaardob/fast-dev-compaction
README states: Codex plugin that wraps session compaction with Jev decisions: before Codex
Evidencehttps://github.com/leonaaardob/fast-dev-compaction/blob/main/src/request.ts#L3
Labelscall-site-verified
luobosibing2/dsh-jev-plugin
README states: Native DeepSeek Harness (DSH) plugin with Jev or Luna Decisions as its judgment model.
Evidencehttps://github.com/luobosibing2/dsh-jev-plugin/blob/main/bench/completion_skill/completion_recovery/runner.py#L56
Labelscall-site-verified
mrnugget/jev-shell-history
README states: (TypeSafe). As you type, the plugin looks at your last 100 distinct history
Evidencehttps://github.com/mrnugget/jev-shell-history/blob/main/src/cli.ts#L5
Labelscall-site-verified
ndolinschi/mcpmatch
README states: User goal → match the best MCP server/capability from a catalog (two-stage when large) via TypeSafe Jev.
Evidencehttps://github.com/ndolinschi/mcpmatch/blob/main/src/app/api/decide/route.ts#L13
Labelscall-site-verified
psygreg/agent-reflex
README states: Plugin for coding agent workflow optimization and safeguarding using any system one decision model, from Jev to self-hosted LM Studio, Ollama or llama.cpp.
Evidencehttps://github.com/psygreg/agent-reflex/blob/main/plugins/hermes/classifier.py#L34
Labelscall-site-verified
ratel-ai/ratel
README states: ratel_jev_plugin(url=None, api_key_env=None, model=None): Jev (TypeSafe AI). Defaults: https://api.typesafe.ai, TYPESAFE_API_KEY, jev-latest.
Evidencehttps://github.com/ratel-ai/ratel/blob/main/src/rankers/python/README.md#L27
Labelsreadme-claim
Ravinder82/jev-flash-router
README states: Zero-token-output decision router MCP server powered by TypeSafe Jev.
Evidencehttps://github.com/Ravinder82/jev-flash-router/blob/main/README.md#L10
Labelsreadme-claim
shimo4228/jev-skill-router
README states: jev-skill-router is a reference implementation for people building with TypeSafe's Jev, a model that writes no text and answers typed questions with probabilities. It is a Claude Code hook: on every prompt it asks Jev wh
Evidencehttps://github.com/shimo4228/jev-skill-router/blob/main/README.md#L15
Labelsreadme-claim
tamaratran/fast-jev-compaction
README states: Claude Code plugin that replaces the compaction summary with Jev decisions:
Evidencehttps://github.com/tamaratran/fast-jev-compaction/blob/main/src/request.ts#L3
Labelscall-site-verified
tamaratran/jev-pruner
README states: A Claude Code plugin that uses TypeSafe's Jev to trim noisy Bash output after
Evidencehttps://github.com/tamaratran/jev-pruner/blob/main/src/jev.ts#L1
Labelscall-site-verified
thruwire/foreman
README states: above slower coding agents. It supports TypeSafe AI's Jev and OpenAI's Decisions API.
Evidencehttps://github.com/thruwire/foreman/blob/main/src/foreman/decision_models/jev.py#L47
Labelscall-site-verified
ussyverse/hermes-jev-router
README states: An opt-in Hermes plugin that uses TypeSafe Jev to assess task complexity and deterministic policy to select an allowed model within configured cost, token, context, latency-estimate and capability constraints.
Evidencehttps://github.com/ussyverse/hermes-jev-router/blob/main/jev.py#L77
Labelscall-site-verified
wobsoriano/oxlint-plugin-jev
README states: A rule is a yes/no question about a function, a call, a JSX element, or a whole file. Each match is sent to Jev with the question, and the plugin reports an error when the yes-probability clears your cutoff.
Evidencehttps://github.com/wobsoriano/oxlint-plugin-jev/blob/main/src/index.ts#L10
Labelscall-site-verified
xienda/dsh-jev-verify
README states: Jev — TypeSafe AI's System One decision model — as a first-class plugin for
Evidencehttps://github.com/xienda/dsh-jev-verify/blob/main/bench/batch-e2e.mjs#L28
Labelscall-site-verified

Browser & computer use

AndrewPrifer/jimothy
README states: Train small, insanely fast local classifiers from Jev-compatible examples. Run locally in your browser or Node.js.
Evidencehttps://github.com/AndrewPrifer/jimothy/blob/master/README.md#L3
Labelsreadme-claim
Bodila51/muse-jev-playbook
README states: Use TypeSafe AI's Jev as a cheap, fast decision layer inside an AI agent workflow — triage, classify, score, and gate work before expensive steps (browser, deep research, retries, subagents).
Evidencehttps://github.com/Bodila51/muse-jev-playbook/blob/main/README.md#L3
Labelsreadme-claim
browser-use/jev-ultrafast
README states:
Evidencehttps://github.com/browser-use/jev-ultrafast/blob/main/jev_ultrafast/model.py#L119
Labelscall-site-verified
droidrun/mobile-jev
README states: One goal. A real Android phone. Jev makes the decisions.
Evidencehttps://github.com/droidrun/mobile-jev/blob/main/scripts/mobile-agent/policy.mjs#L224
Labelscall-site-verified
ethanplusai/jev-chat-for-twitch
README states: Sign up at typesafe.ai and create an API key. The key stays in your browser profile. You pay TypeSafe directly for what you use.
Evidencehttps://github.com/ethanplusai/jev-chat-for-twitch/blob/main/README.md#L28
Labelsreadme-claim
filedcom/playjev
README states: Stagehand, but with Jev. Natural-language browser automation for Playwright, powered by Jev.
Evidencehttps://github.com/filedcom/playjev/blob/main/src/core/playjev.ts#L305
Labelscall-site-verified
forvela/jev-agent-browser
README states: Give a parent agent a bounded browser task. Jev chooses the next typed action. agent-browser executes it. Ambiguity, repetition, or a stuck state becomes a structured handoff back to the parent.
Evidencehttps://github.com/forvela/jev-agent-browser/blob/main/src/decision.js#L1
Labelscall-site-verified
idovmamane/dejevu
README states: Jev? Déjà vu. Browser agents that run on instinct, no Jev needed. One look at the page. One call to any open model. One action.
Evidencehttps://github.com/idovmamane/dejevu/blob/main/dejevu/policy.py#L209
Labelscall-site-verified
jkudish/jev-browser
README states:
Evidencehttps://github.com/jkudish/jev-browser/blob/main/src/questions.ts#L4
Labelscall-site-verified
Liyucheng1997/332_lab-jev-chat
README states: 采集：一个 App 一个适配器（app/src/main/java/com/jev/probe/capture/ChatAppAdapter.kt），服务按前台包名分发；适配器只负责把当前窗口变成「标题 + 消息列表（谁说的、说了什么）」，下游判断 / 悬浮窗 / 填入全部通用。微信适配器读聊天气泡（com.tencent.mm:id/bkl），按气泡位置判断谁说的；QQ 适配器读正文节点（com.tencent.mobileqq:id
Evidencehttps://github.com/Liyucheng1997/332_lab-jev-chat/blob/main/README.md#L50
Labelsreadme-claim
michaelswissa/jevry
README states: The historical beta.1 study ran three five-turn sessions per implementation, with the same fixture tasks and resolved Claude model. Jevry also used Jev for browser decisions.
Evidencehttps://github.com/michaelswissa/jevry/blob/main/desktop/engine.ts#L205
Labelscall-site-verified
ndolinschi/swarmrouter
README states: Pick which agent/skill handles a task (research / code / browser / support / writer) + confidence — visual swarm map powered by TypeSafe Jev.
Evidencehttps://github.com/ndolinschi/swarmrouter/blob/main/src/app/api/decide/route.ts#L7
Labelscall-site-verified
phyous/tsai-civ2
README states: An original Civilization II browser harness for TypeSafe Jev, with live decision
Evidencehttps://github.com/phyous/tsai-civ2/blob/main/civ2/session.py#L486
Labelscall-site-verified
pst2154/Nemotron_Jev
README states: Ask typed questions about text or JSON and inspect model-derived probability distributions in a browser. One container runs the model, the original Decision Lab explorer, and a TypeSafe-shaped API.
Evidencehttps://github.com/pst2154/Nemotron_Jev/blob/master/README.md#L3
Labelsreadme-claim
rokcso/bluenoise
README states: BlueNoise collects no telemetry or analytics. It does not read cookies, access account credentials, call X APIs, or take account actions such as blocking, muting, following, or posting. Settings and rules are stored thro
Evidencehttps://github.com/rokcso/bluenoise/blob/main/README.md#L34
Labelsreadme-claim
Sac-Y/Jev-cu
README states: 把 Computer Use 的「下一步点哪里」交给 Jev（TypeSafe System One）：Jev 从界面文字候选中选元素、动作、完成度与风险，Codex Computer Use 负责读取界面与执行，本地策略门槛拦截敏感操作。只传文字，不传截图。
Evidencehttps://github.com/Sac-Y/Jev-cu/blob/main/scripts/jev-decide.mjs#L19
Labelscall-site-verified
yikangy873-gif/jev-desktop
README states: Jev Desktop adds a bounded decision loop to Codex Computer Use for browser tabs and native macOS apps.
Evidencehttps://github.com/yikangy873-gif/jev-desktop/blob/main/plugins/jev-desktop/scripts/bridge-client.mjs#L14
Labelscall-site-verified
Ying-Kai-Liao/jev-browser
README states: jev-browser runs locally. It has no server of its own and collects no telemetry. To decide
Evidencehttps://github.com/Ying-Kai-Liao/jev-browser/blob/main/README.md#L362
Labelsreadme-claim

Applications

Jev RAG
After retrieval, Jev decides whether the passages actually support an answer, and only then is generation allowed to run.
Evidencehttps://github.com/aifabrice/jev-rag
Labelspublic-sourcereadme-claim
jev-research-pipeline
Hands each convergence check in the research pipeline to Jev so open-ended text cannot drift between steps.
Evidencehttps://github.com/shimo4228/jev-research-pipeline/blob/main/src/jev_research_pipeline/pipeline/drift.py#L21
Labelspublic-sourcecall-site-verified
Cribrix
Jev routes the query, filters retrieved passages and verifies claims before any answer is released.
Evidencehttps://github.com/david96182/cribrix/blob/main/cribrix/clients/jev.py#L4
Labelspublic-sourcecall-site-verified
JEV Book Tags
Jev decides a book genre and how well the evidence supports it; tags are written into Calibre only above the threshold.
Evidencehttps://github.com/iamjonatha/jev-book-tags/blob/main/plugin/client.py#L7
Labelspublic-sourcecall-site-verified
advocaat
Requests the gateway with typesafe-ai/jev as the model id, treating Jev as a pluggable judgment backend.
Evidencehttps://github.com/pithings/advocaat/blob/main/src/api.ts#L127
Labelspublic-sourcecall-site-verified
arimanyus/warrenduffer
README states: Dashboard: SSH tunnel or Tailscale to http://127.0.0.1:8080. Set the capital Jev can deploy in the header. Kill = cancel all entries and flatten; Resume clears it.
Evidencehttps://github.com/arimanyus/warrenduffer/blob/main/src/context.ts#L42
Labelscall-site-verified
dabit3/jev-experiments
README states: sent only to api.typesafe.ai from the native process; it is never written to disk by the app
Evidencehttps://github.com/dabit3/jev-experiments/blob/main/jev-ax-pilot/README.md#L153
Labelsreadme-claim
DevMortimer/pi-typesafe
README states: A tool for the agent. typesafe_evaluate hands small structured judgments (classify, triage, compare, score) to Jev and returns calibrated numbers in one batched call.
Evidencehttps://github.com/DevMortimer/pi-typesafe/blob/main/src/ask.ts#L32
Labelscall-site-verified
GeekLinkDev/jev-subtitle-translator
README states: An open-source SRT translator and subtitle QC tool for LLM-powered workflows. Use it to translate SRT files, preserve every subtitle cue, and automatically check translations with Jev.
Evidencehttps://github.com/GeekLinkDev/jev-subtitle-translator/blob/main/README.md#L7
Labelsreadme-claim
iamaamir/system-one
README states: Use TypeSafe Jev today, Reflex locally, any compatible /v1/systemone endpoint, or your own SystemOneProvider tomorrow. Your application keeps the same choice, noul, and score code.
Evidencehttps://github.com/iamaamir/system-one/blob/main/pi-system-one/src/debug.ts#L7
Labelscall-site-verified
kraayenjon/jev-linkedin-saved-classifier
README states: open saved posts -> read every card -> one Jev call each -> live dashboard -> board + csv + json
Evidencehttps://github.com/kraayenjon/jev-linkedin-saved-classifier/blob/main/src/jev_linkedin_saved/cli.py#L38
Labelscall-site-verified
mattneel/typesafe
README states: and its Jev model. Ask typed Choice, Noul and Score questions about your application's state in
Evidencehttps://github.com/mattneel/typesafe/blob/master/lib/typesafe.ex#L252
Labelscall-site-verified
mattneel/typesafe.zig
README states: Jev model. Ask typed Noul, Choice and Score questions about your application's state in one
Evidencehttps://github.com/mattneel/typesafe.zig/blob/master/src/Client.zig#L353
Labelscall-site-verified
ndolinschi/spendbrake
README states: Budget + plan → continue / downgrade_model / stop — cost×value dashboard powered by TypeSafe Jev.
Evidencehttps://github.com/ndolinschi/spendbrake/blob/main/src/app/api/decide/route.ts#L7
Labelscall-site-verified
nekuda-ai/WindTunnel
README states: tasks are scored by inspecting the application, and published final answers are redacted. The Jev release includes
Evidencehttps://github.com/nekuda-ai/WindTunnel/blob/main/experiments/jev/frozen/arms/decision-providers.mjs#L60
Labelscall-site-verified
ReallyArtificial/jev-by-example
README states: Ten runnable experiments in building agents that know what to do next—and when to ask. Each combines a small Jev judgment with application logic you can read, change, and test.
Evidencehttps://github.com/ReallyArtificial/jev-by-example/blob/main/src/client.mjs#L4
Labelscall-site-verified
ronadin2002/jev-cua
README states: A small floating bar for voice and text commands. Jev picks the next action from your Mac’s live controls, the app executes it, and the loop continues toward your request.
Evidencehttps://github.com/ronadin2002/jev-cua/blob/main/Sources/Core.swift#L21
Labelscall-site-verified
tostechbr/partway
README states: It asks Jev, TypeSafe's System One model, about every word you say. Jev answers with typed decisions and probabilities, not text, in about 200 ms, so the app can act mid-sentence and wait only when it has to.
Evidencehttps://github.com/tostechbr/partway/blob/main/README.md#L22
Labelsreadme-claim
yusukebe/hono-jev-router
README states: app.on('jev', ' ', handler) registers a semantic route.
Evidencehttps://github.com/yusukebe/hono-jev-router/blob/main/README.md#L51
Labelsreadme-claim
Zefan-Cai/Open-Jev
README states: Open-Jev-27B-v1.1 is here. Give your app a decision, with probabilities.
Evidencehttps://github.com/Zefan-Cai/Open-Jev/blob/main/README.md#L3
Labelsreadme-claim

Games & simulations

iammusham/jev-snake
README states: The project includes a browser-based human baseline and a pygame experiment client. Jev mode uses the same Python engine, replacing only the source of each requested direction.
Evidencehttps://github.com/iammusham/jev-snake/blob/main/snake_game/jev_agent.py#L65
Labelscall-site-verified
lukaske/jev-doom-agent
README states: The vendored GPL Chocolate Doom fork lives in vendor/chocolate-doom. browser_doom_bridge.c exposes the real engine's health, armor, ammo, damage, coordinates, kills, line-of-sight monsters, and visible pickups to JavaScr
Evidencehttps://github.com/lukaske/jev-doom-agent/blob/main/README.md#L18
Labelsreadme-claim
valentynkit/jev-plays-pokemon-red
README states: ticks and only calls Jev where the game actually branches. Between the bedroom and Oak's
Evidencehttps://github.com/valentynkit/jev-plays-pokemon-red/blob/main/src/jpp/policy.py#L20
Labelscall-site-verified
wuyoscar/jev-skill
README states: | Demo | Doom & Wikiracing | Watch the official game demos; no standalone repo linked on this page. | Author demo |
Evidencehttps://github.com/wuyoscar/jev-skill/blob/main/README.md#L143
Labelsreadme-claim

Demos & playgrounds

Trio-Spark demos
Shows where a typed decision lands inside an interactive flow, instead of treating generated text as the result.
Evidencehttps://github.com/machinefi/trio-spark
Labelspublic-sourcedemo-only
juancamiloqhz/roverlab
README states: A browser-based planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI.
Evidencehttps://github.com/juancamiloqhz/roverlab/blob/main/server/decisions.ts#L1
Labelscall-site-verified
sdras/jev-webmcp-extension
README states: Inspecting requests in the playground. Select “Open in playground” to load the request's state and questions into the TypeSafe playground.
Evidencehttps://github.com/sdras/jev-webmcp-extension/blob/main/src/jev.js#L4
Labelscall-site-verified
wondertwins/jev-benchmark
README states: Everything is here: the code, the labeled data, every raw request and response (runs/raw/), the metrics, and an interactive playground. Model served as jev-1.13.0 on 2026-09-16.
Evidencehttps://github.com/wondertwins/jev-benchmark/blob/main/jevchess/experiments.py#L22
Labelscall-site-verified

Benchmarks & research

Decision Models as Guardrails
Treats typed decisions as guardrails rather than scores, using fixed options to constrain the action set downstream can execute.
Evidencehttps://github.com/raxITlabs/decision-models-as-guardrails/blob/main/infra/gcp/laya_server.py#L118
Labelspublic-sourceauthor-reported-metriccall-site-verified
anandi1989/awesome-jev-usecases
README states: ts2.tech: "TypeSafe AI Raises $40 Million for Jev, but Its 445× Cost Claim Is Still Self-Tested": *The skeptical audit of self-tested benchmarks, plus funding verification.*
Evidencehttps://github.com/anandi1989/awesome-jev-usecases/blob/main/README.md#L234
Labelsreadme-claim
caiovicentino/eikos
README states: evaluation/eval_jev_suite.py and evaluation/eval_laya_suite.py run the same suites through Jev (API, evaluation
Evidencehttps://github.com/caiovicentino/eikos/blob/main/eikos/serve.py#L343
Labelscall-site-verified
codeitlikemiley/system-one-adapter-rust
README states: A drop-in replacement for TypeSafe's system_one evaluation API, backed by LLM
Evidencehttps://github.com/codeitlikemiley/system-one-adapter-rust/blob/main/src/client.rs#L15
Labelscall-site-verified
erboland/jev-fund
README states: jev-fund: Open-Source Paper Hedge Fund
Evidencehttps://github.com/erboland/jev-fund/blob/main/README.md#L32
Labelsreadme-claim
frankda/jev-poly-crypto-demo
README states: This version implements a live market-data adapter, Jev integration, paper trading and a dashboard. It does not connect a wallet or submit real orders. TRADING_MODE=live is rejected at startup.
Evidencehttps://github.com/frankda/jev-poly-crypto-demo/blob/main/scripts/check-jev.ts#L2
Labelscall-site-verified
fstandhartinger/jevbench
README states: Jev is TypeSafe AI's decision model; JevBench also evaluates Jev-compatible systems. The canonical JevBench board is https://benchmarkheaven.com/jev-models.
Evidencehttps://github.com/fstandhartinger/jevbench/blob/main/README.md#L5
Labelsreadme-claim
grmkris/robo-harness
README states: Decision runs (bun run jev) let an evaluation model or rules baseline pick bounded joint steps; chat and a decision run never move the arm at the same time.
Evidencehttps://github.com/grmkris/robo-harness/blob/main/apps/server/src/decision/strategies.ts#L273
Labelscall-site-verified
kylemclaren/jevpdf
README states: Cheap enough to ask about every line. Jev costs $0.042 per million input tokens, and output is free. Checking every line of a 15-page paper costs well under a cent.
Evidencehttps://github.com/kylemclaren/jevpdf/blob/main/server/jev-upstream.ts#L5
Labelscall-site-verified
micytao/vllm-playground
README states: Decision Models (Experimental) — A brand-new sandbox tab for structured-read decisions powered by DiffusionGemma and Jev / System One. Gallery of 12 use cases across 4 tabbed categories (Noul, Choice, Score, Combination)
Evidencehttps://github.com/micytao/vllm-playground/blob/main/README.md#L37
Labelsreadme-claim
nexibeo/jev-cookbook
README states: Practical, tested recipes for TypeSafe's Jev, the fast decision model on OpenRouter. Fifteen real-world jobs, each with a runnable script, a small labelled dataset and measured results: support triage, database indexing,
Evidencehttps://github.com/nexibeo/jev-cookbook/blob/main/README.md#L5
Labelsreadme-claim
nickthompson480/typesafe-ai-playground
README states: You need Python 3.10 or newer, a modern browser, and a TypeSafe API key to run evaluations. There are no packages to install and no frontend build step.
Evidencehttps://github.com/nickthompson480/typesafe-ai-playground/blob/main/server.py#L17
Labelscall-site-verified
pedronauck/skills
README states: jev-engineering — Design and build use cases, POCs and production systems with TypeSafe's Jev decision model (System One): design modes and use-case archetypes, decision state, typed questions, Jev combined with generati
Evidencehttps://github.com/pedronauck/skills/blob/main/README.md#L80
Labelsreadme-claim
theSekyi/jevusecases
README states: A directory of real projects, filtered by what they replace, whether they've been benchmarked, and whether there's code to copy — not a marketing site for Jev itself.
Evidencehttps://github.com/theSekyi/jevusecases/blob/main/README.md#L5
Labelsreadme-claim
unicodeveloper/jevocks
README states: Jevinik uses Jev, TypeSafe AI's System One evaluation model, to make typed, probabilistic decisions without calling a general-purpose generative LLM.
Evidencehttps://github.com/unicodeveloper/jevocks/blob/main/README.md#L11
Labelsreadme-claim
willkelly/jev-evaluation
README states: An adversarial evaluation of jev, the decision model sold by TypeSafe. It
Evidencehttps://github.com/willkelly/jev-evaluation/blob/main/jeveval/config.py#L18
Labelscall-site-verified

Other lists

0x7067/claude-jev
README states: The run sends your past prompts to api.typesafe.ai. Start with --sample 250
Evidencehttps://github.com/0x7067/claude-jev/blob/main/eval/README.md#L130
Labelsreadme-claim
0xArx/jevegis
README states: retrieved documents) and Trust & Safety moderation, both powered by TypeSafe's Jev
Evidencehttps://github.com/0xArx/jevegis/blob/main/src/lib/engine.ts#L1
Labelscall-site-verified
0xBakeer/arbiter
README states: Serve typed-decision models — Laya or your own — on your GPU or your Mac, with a Jev-compatible
Evidencehttps://github.com/0xBakeer/arbiter/blob/main/integrations/claude-code/hooks/eval.py#L57
Labelscall-site-verified
0xNatoshi/jev-codex-router
README states: Jev chooses a model and thinking effort together for each model call, including
Evidencehttps://github.com/0xNatoshi/jev-codex-router/blob/main/poc/backtest_savings.py#L157
Labelscall-site-verified
0xtrou/rubikjev
README states: You scramble like a menace. Jev — the in-house AI solver — judges the chaos, roasts you, and cooks the solve live.
Evidencehttps://github.com/0xtrou/rubikjev/blob/main/src/app/api/solve/route.ts#L127
Labelscall-site-verified
2FastLabs/agent-squad
README states: ⚡ Fast and cheap — sub-second decisions billed on input tokens only (output tokens free, see pricing), versus a full LLM call per routing decision.
Evidencehttps://github.com/2FastLabs/agent-squad/blob/main/README.md#L157
Labelsreadme-claim
3clyp50/a0-typesafe-ai
README states: Ask Jev focused questions and get typed answers with probability cards in Agent Zero's chat. One typesafe_query call can combine Choice, Noul, Score, and Box questions over the same text and images.
Evidencehttps://github.com/3clyp50/a0-typesafe-ai/blob/main/extensions/webui/get_tool_message_handler/typesafe.js#L2
Labelscall-site-verified
6Mikao9/jev-agent-design-with-topk-logits-choices
README states: Jev is the first backend we use for live experiments; the runtime API is
Evidencehttps://github.com/6Mikao9/jev-agent-design-with-topk-logits-choices/blob/main/jev_agent/jev_client.py#L57
Labelscall-site-verified
Aayan-DEV/aayans-yc-indexor
README states: Put a TypeSafe key in .env.local as TYPE_SAFE_KEY. Get one at typesafe.ai.
Evidencehttps://github.com/Aayan-DEV/aayans-yc-indexor/blob/main/README.md#L30
Labelsreadme-claim
AbdelStark/bicameral
README states: Sent to TypeSafe (POST /v1/systemone via TypeSafeClient.systemOne): redacted, truncated JSON state for the current reflex (goal, proposed tool, compact diffs, recent action summaries) and the pack's questions.
Evidencehttps://github.com/AbdelStark/bicameral/blob/main/packages/s1-runtime/src/backends/typesafe.ts#L1
Labelscall-site-verified
abe75ch/tiltmeter
README states: Notices your Jev decisions tilting before anything visibly breaks.
Evidencehttps://github.com/abe75ch/tiltmeter/blob/main/tiltmeter.py#L270
Labelscall-site-verified
AboveColin/HA-Jev
README states: back. Jev is a decision model, not a chat model. It answers a typed question with a
Evidencehttps://github.com/AboveColin/HA-Jev/blob/main/README.md#L12
Labelsreadme-claim
ad-si/cai
README states: [TypeSafe]: https://docs.typesafe.ai/models
Evidencehttps://github.com/ad-si/cai/blob/main/readme.md#L50
Labelsreadme-claim
adarshmishra07/jcm-router
README states: level per message, using TypeSafe's Jev classifier. Trivial questions go to Haiku, everyday work to
Evidencehttps://github.com/adarshmishra07/jcm-router/blob/main/scripts/eval.ts#L12
Labelscall-site-verified
adhyaay-karnwal/jev-chat
README states: A research decoder that treats Jev (a System One decision model) as if it were a language model.
Evidencehttps://github.com/adhyaay-karnwal/jev-chat/blob/main/src/jevchat/client.py#L7
Labelscall-site-verified
affirmitv/ghosthands
README states: Configuration: GH_PLANNER=jev, GH_JEV_MODEL (default typesafe/jev-1.13; ~typesafe/jev-latest
Evidencehttps://github.com/affirmitv/ghosthands/blob/main/README.md#L221
Labelsreadme-claim
afshinm/laya-mps
README states: Run Jev-style typed decisions locally on your Mac with low RAM usage and fast responses.
Evidencehttps://github.com/afshinm/laya-mps/blob/main/README.md#L3
Labelsreadme-claim
Ai-trainee/awesome-jev
README states: prism-liquidity-agent — ★69 · TypeScript · Jev 评分 18 · 工具与产品 — Solana 流动性代理：可选的 Jev 影子判定用于存款选择、有毒流与市场状态压力。
Evidencehttps://github.com/Ai-trainee/awesome-jev/blob/main/README.md#L390
Labelsreadme-claim
ai4curation/jevotron
README states: in tabular, structured, and text files, SQLite, and DuckDB, powered by Jev.
Evidencehttps://github.com/ai4curation/jevotron/blob/main/README.md#L8
Labelsreadme-claim
AiPersonacademy/jev-resume-disqualifier
README states: Automated Candidate Knockout Engine for High-Volume Recruiting — Powered by TypeSafe Jev System One Decision Intelligence.
Evidencehttps://github.com/AiPersonacademy/jev-resume-disqualifier/blob/main/engine/decision_gateway.py#L20
Labelscall-site-verified
alexj11324/open-jev-approvals
README states: When the agent is about to run a tool, a hook intercepts the call, TypeSafe
Evidencehttps://github.com/alexj11324/open-jev-approvals/blob/main/internal/jev/client.go#L22
Labelscall-site-verified
allebee/pytest-jev
README states: All the claims about one text go to Jev in a single request. When a prompt change breaks the reply,
Evidencehttps://github.com/allebee/pytest-jev/blob/main/bench/llm_judge.py#L14
Labelscall-site-verified
allenporter/home-assistant-typesafe
README states: Queries the TypeSafe System One API (jev-latest) in a single network roundtrip, obtaining calibrated probabilities across all questions without hallucination or token streaming latency.
Evidencehttps://github.com/allenporter/home-assistant-typesafe/blob/main/README.md#L34
Labelsreadme-claim
alterhq/typesafe-sdk-swift
README states: authenticated backend. Keep the TypeSafe API key in server-side secret storage. Direct API-key
Evidencehttps://github.com/alterhq/typesafe-sdk-swift/blob/main/Sources/TypeSafe/Requests.swift#L4
Labelscall-site-verified
altryne/jevify
README states: Use Jev during everyday agent work, and find what it can improve in your product.
Evidencehttps://github.com/altryne/jevify/blob/main/scripts/jev_client.py#L32
Labelscall-site-verified
andrelandgraf/safer-with-jev
README states: Public showcases of TypeSafe Jev judgments. TypeSafe Jev inspects the body, then optionally forwards the same bytes to a caller-chosen HTTPS URL.
Evidencehttps://github.com/andrelandgraf/safer-with-jev/blob/main/src/index.ts#L5
Labelscall-site-verified
andududu/jeview
README states: your code → Jeview (127.0.0.1:4777) → TypeSafe (api.typesafe.ai)
Evidencehttps://github.com/andududu/jeview/blob/main/README.md#L9
Labelsreadme-claim
Anil-matcha/awesome-jev-by-typesafe
README states: ▶ Watch: Jev: 8 Wild Things People Already Built With TypeSafe's New AI Model
Evidencehttps://github.com/Anil-matcha/awesome-jev-by-typesafe/blob/main/README.md#L14
Labelsreadme-claim
aniruddh-krovvidi/switchboard
README states: A guardrail and model router for LLM gateways, built on Jev, TypeSafe AI's
Evidencehttps://github.com/aniruddh-krovvidi/switchboard/blob/main/jev.py#L3
Labelscall-site-verified
anishfn/shapeshift
README states:
Evidencehttps://github.com/anishfn/shapeshift/blob/main/src/lib/jev/client.ts#L2
Labelscall-site-verified
AnotiaWang/awesome-jev
README states: Open-source products and demos that put a decision model in a real loop. Most use Jev today.
Evidencehttps://github.com/AnotiaWang/awesome-jev/blob/main/README.md#L178
Labelsreadme-claim
AntonioCoppe/jev-harness
README states: It is not affiliated with TypeSafe. You need a TypeSafe API key to call Jev.
Evidencehttps://github.com/AntonioCoppe/jev-harness/blob/main/recipes/agent-comm-harness/message-route.ts#L1
Labelscall-site-verified
AppitStudio/awesome-jev
README states: Discover Jev-powered apps, developer resources, and runnable decision examples.
Evidencehttps://github.com/AppitStudio/awesome-jev/blob/main/README.md#L3
Labelsreadme-claim
AppSprout-dev/Unsga3
README states: TypeSafe / Jev Pareto scoring (optional)
Evidencehttps://github.com/AppSprout-dev/Unsga3/blob/main/README.md#L104
Labelsreadme-claim
ARCJ137442/jev-life
README states: Alongside it sits a Jev-compatible broker that wraps any OpenAI- or Anthropic-compatible LLM into a Jev backend,
Evidencehttps://github.com/ARCJ137442/jev-life/blob/main/src/client/api.ts#L222
Labelscall-site-verified
arczhi/jet
README states: Judgment-first routing — Jev (TypeSafe System One) handles context
Evidencehttps://github.com/arczhi/jet/blob/main/README.md#L43
Labelsreadme-claim
atharvamhaske/typesafe-sdk-go
README states: | WithBaseURL | TYPESAFE_BASE_URL | API base URL, defaults to https://api.typesafe.ai |
Evidencehttps://github.com/atharvamhaske/typesafe-sdk-go/blob/main/README.md#L115
Labelsreadme-claim
audreyt/paseo-spacedock
README states: Gate judgment (Jev / TypeSafe-compatible)
Evidencehttps://github.com/audreyt/paseo-spacedock/blob/main/README.md#L56
Labelsreadme-claim
automateyournetwork/netclaw
README states: | JEV_BASE_URL | https://api.typesafe.ai; /v1/systemone appended when no path supplied; full custom paths accepted |
Evidencehttps://github.com/automateyournetwork/netclaw/blob/main/mcp-servers/jev-mcp/README.md#L42
Labelsreadme-claim
Avinash-jetwani/jevmem
README states: To TypeSafe AI, https://api.typesafe.ai/v1/systemone, or the URL in TYPESAFE_BASE_URL if you set it:
Evidencehttps://github.com/Avinash-jetwani/jevmem/blob/main/plugin/README.md#L46
Labelsreadme-claim
awlevin/typesafe-computer-use
README states:
Evidencehttps://github.com/awlevin/typesafe-computer-use/blob/main/typesafe_computer_use/actions.py#L9
Labelscall-site-verified
awslabs/agentcore-samples
README states: Jev Evaluators (--with-jev)
Evidencehttps://github.com/awslabs/agentcore-samples/blob/main/01-features/06-observe-evaluate-optimize-your-agent/02-evaluate/custom-code-based-evaluation/README.md#L600
Labelsreadme-claim
Ayush0054/metis
README states: metis-workflow is a small Python framework for workflows powered by TypeSafe AI's
Evidencehttps://github.com/Ayush0054/metis/blob/main/legacy/metis-triage/src/metis_triage/_triage.py#L154
Labelscall-site-verified
Baba88611/detroit-ai-player
README states: Select the dedicated TypeSafe backend with --model jev. Append these variables to your local 03_runner/.env, preserving existing configuration. Keep the real key local:
Evidencehttps://github.com/Baba88611/detroit-ai-player/blob/main/README.md#L189
Labelsreadme-claim
bcharleson/jev-gtm-cookbook
README states: Open-source go-to-market recipes built on TypeSafe's Jev: code does the work, Jev makes the judgment calls, and each recipe runs locally on data you already own.*
Evidencehttps://github.com/bcharleson/jev-gtm-cookbook/blob/main/README.md#L5
Labelsreadme-claim
beamnxw/minelog
README states: Jev (TypeSafe System One) picks one bounded action from a closed catalog, plus a safety noul and an urgency score. Fast. Typed. No prose.
Evidencehttps://github.com/beamnxw/minelog/blob/main/README.md#L33
Labelsreadme-claim
BeatAPI/awesome-jev
README states:
Evidencehttps://github.com/BeatAPI/awesome-jev/blob/main/scripts/curate-star50-expansion-2026-09-23.mjs#L217
Labelscall-site-verified
BenCaunt/jev-box-tracking
README states: jev-box-tracking
Evidencehttps://github.com/BenCaunt/jev-box-tracking/blob/main/README.md#L1
Labelsreadme-claim
bestagentkits/jev-skillful
README states: The prompt is sent to api.typesafe.ai as part of the routing request. This is the only kind of
Evidencehttps://github.com/bestagentkits/jev-skillful/blob/main/packages/cli/src/core/eval/replay.ts#L22
Labelscall-site-verified
Bewinxed/jevgpt
README states: TypeSafe AI's jev-latest is a decision model: it does not generate text,
Evidencehttps://github.com/Bewinxed/jevgpt/blob/master/src/jevgpt/sampler.py#L29
Labelscall-site-verified
bhaiG-de/jev-design-test
README states: Prerequisites: Node 20+, and a Jev (TypeSafe) API key.
Evidencehttps://github.com/bhaiG-de/jev-design-test/blob/master/vite.config.ts#L5
Labelscall-site-verified
BillionsBobby/JevRouter
README states:
Evidencehttps://github.com/BillionsBobby/JevRouter/blob/main/src/provider.ts#L103
Labelscall-site-verified
bladedevoff/stuntd
README states: With the paid Jev API in front, the same demo runs with it as the teacher instead: put
Evidencehttps://github.com/bladedevoff/stuntd/blob/main/examples/banking/README.md#L42
Labelsreadme-claim
bodepudimuneendra-netizen/laya-jev-GraphRAG
README states: │ LAYER 2 — DECISION (Laya / Jev) ← The CPU │
Evidencehttps://github.com/bodepudimuneendra-netizen/laya-jev-GraphRAG/blob/main/graphrag_neo4j_laya/graphrag/models/jev.py#L7
Labelscall-site-verified
bohutang/sift
README states: Search results stay native: no Jev scoring, local filters, labels, or collapsed posts on /search. The normal feed and post pages still use your filtering settings.
Evidencehttps://github.com/bohutang/sift/blob/main/background.js#L4
Labelscall-site-verified
brainstormity/Jev-X-Sentiment-Analysis
README states: An on-demand crypto market intelligence and decision-support terminal powered by TypeSafe AI's System One model (Jev).
Evidencehttps://github.com/brainstormity/Jev-X-Sentiment-Analysis/blob/main/app/services/typesafe_service.py#L3
Labelscall-site-verified
brandonbryant12/transcript-scorecard
README states: Server-side OpenAI Decisions and TypeSafe JEV adapters for incremental transcript scoring
Evidencehttps://github.com/brandonbryant12/transcript-scorecard/blob/main/apps/api/src/classifier.ts#L1
Labelscall-site-verified
brnyxx/jev-ra
README states:
Evidencehttps://github.com/brnyxx/jev-ra/blob/main/jev_ra/config.py#L11
Labelscall-site-verified
buberlo/jev-trader
README states: jev-trader
Evidencehttps://github.com/buberlo/jev-trader/blob/main/README.md#L1
Labelsreadme-claim
bugkiwi/elons-job
README states: TypeSafe 请求使用 https://api.typesafe.ai/v1/systemone；API 返回不符合预期、超时、401、429 或 5xx 时 Fail Open。
Evidencehttps://github.com/bugkiwi/elons-job/blob/main/README.md#L46
Labelsreadme-claim
BunsDev/typesafe-ai-playground
README states: Small experiments. Clear decisions. This is an independent community project, not an official TypeSafe AI product, production agent harness, or claim that a typed answer is correct.
Evidencehttps://github.com/BunsDev/typesafe-ai-playground/blob/main/lib/serverJev.ts#L52
Labelscall-site-verified
BunsDev/typesafe-ui
README states: Reusable React components and interactive interface patterns for TypeSafe AI projects, built with shadcn/ui, Base UI, and Tailwind CSS.
Evidencehttps://github.com/BunsDev/typesafe-ui/blob/main/README.md#L3
Labelsreadme-claim
burnigtm/jev-mcp
README states: codex mcp add jev --env TYPESAFE_API_KEY=ts_... -- node /absolute/path/to/jev-mcp/dist/index.js
Evidencehttps://github.com/burnigtm/jev-mcp/blob/main/src/errors.ts#L1
Labelscall-site-verified
BYK/jev-mcp
README states: Most Jev integrations expose "ask the model a question". The hard part in practice is not asking —
Evidencehttps://github.com/BYK/jev-mcp/blob/main/src/tools/ask.ts#L37
Labelscall-site-verified
bytelabs-oss/clash-jev
README states: play around with it. I built clash-jev, a bot that uses Jev to make near real-time decisions on live
Evidencehttps://github.com/bytelabs-oss/clash-jev/blob/main/clash_jev/policy.py#L183
Labelscall-site-verified
caiovicentino/eikos-arena
README states: MIT) against Jev (TypeSafe's decision API). Every 5 minutes both get the same market snapshot and the same 28
Evidencehttps://github.com/caiovicentino/eikos-arena/blob/main/arena/arena.py#L31
Labelscall-site-verified
can1357/jegrep
README states: src/jev.rs 0.97 · 458 lines shown
Evidencehttps://github.com/can1357/jegrep/blob/main/README.md#L122
Labelsreadme-claim
CaptainCore/captaincore
README states: Optional integrations -- fathom_api_key (analytics) and typesafe_api_key (the TypeSafe decision API behind captaincore typesafe and scan --triage; TYPESAFE_API_KEY in the environment works too)
Evidencehttps://github.com/CaptainCore/captaincore/blob/master/typesafe/client.go#L188
Labelscall-site-verified
carldaws/hunch
README states: Point Hunch at a System One endpoint. Jev is available through
Evidencehttps://github.com/carldaws/hunch/blob/main/README.md#L27
Labelsreadme-claim
carlosedm10/agi-jev-containment
README states: What is Jev in this project? Jev is TypeSafe System One (jev-1.13.0): a semantic classifier that answers typed questions (criticality L0–L5, intent, concealment, …) over short-term tape + long-term key nodes. It does not
Evidencehttps://github.com/carlosedm10/agi-jev-containment/blob/main/README.md#L70
Labelsreadme-claim
cbruyndoncx/AskJev-MCP
README states: Ask everything you want to know about a state in one call rather than several — TypeSafe bills per
Evidencehttps://github.com/cbruyndoncx/AskJev-MCP/blob/main/src/index.ts#L6
Labelscall-site-verified
cequence-io/openai-scala-client
README states: Decision models give typed answers with calibrated probabilities. Two APIs serve them - TypeSafe AI's System One
Evidencehttps://github.com/cequence-io/openai-scala-client/blob/master/typesafe-client/src/main/scala/io/cequence/openaiscala/typesafe/JsonFormats.scala#L125
Labelscall-site-verified
Chandler-Sun/chat2jev
README states: Convert OpenAI-compatible Chat Completions requests into TypeSafe System One (Jev) State / Questions, compare generated text with structured judgments, and publish reusable question sets as proxy routes.
Evidencehttps://github.com/Chandler-Sun/chat2jev/blob/main/src/components/answers.tsx#L49
Labelscall-site-verified
CharlesFeng0314/JEV_sees
README states: JEV is fast, structured, and built to make decisions.
Evidencehttps://github.com/CharlesFeng0314/JEV_sees/blob/main/jev_sees/__init__.py#L3
Labelscall-site-verified
Charlyhno-eng/jev-document-classification
README states: To use JEV, you need a Vercel account and an AI Gateway API key.
Evidencehttps://github.com/Charlyhno-eng/jev-document-classification/blob/main/README.md#L25
Labelsreadme-claim
cheeaun/jevmoji
README states: Type up to 40 characters. Get related emojis scored by TypeSafe’s Jev — many matches, not just one.
Evidencehttps://github.com/cheeaun/jevmoji/blob/main/README.md#L10
Labelsreadme-claim
CheshiAI/Cheshi
README states: Previous conversation recall is off by default, including for existing TypeSafe
Evidencehttps://github.com/CheshiAI/Cheshi/blob/main/README.md#L86
Labelsreadme-claim
chez-shanpu/typesafeai-go
README states: // A TypeSafe AI compatible server running locally without authentication.
Evidencehttps://github.com/chez-shanpu/typesafeai-go/blob/main/option.go#L9
Labelscall-site-verified
christos-antono/NPCTalk
README states: | Actions and spoken orders | TypeSafe | TYPESAFE_API_KEY |
Evidencehttps://github.com/christos-antono/NPCTalk/blob/main/README.md#L57
Labelsreadme-claim
chy4pro/jev-for-chrome
README states: | OpenRouter | https://openrouter.ai/api/alpha/decisions | typesafe/jev-1.13 |
Evidencehttps://github.com/chy4pro/jev-for-chrome/blob/main/README.md#L112
Labelsreadme-claim
cobanov/awesome-jev
README states: New: Ollaya runs open decision models locally behind a Jev-compatible API.
Evidencehttps://github.com/cobanov/awesome-jev/blob/main/README.md#L8
Labelsreadme-claim
cobusgreyling/Jev
README states: Jev Showcase — TypeSafe System One, not chat
Evidencehttps://github.com/cobusgreyling/Jev/blob/main/README.md#L1
Labelsreadme-claim
cocktailpeanut/jevthoven
README states: There is no offline composer, audio model, or hidden song library. Every note traces to a persisted Jev decision (or a labeled fixture/manual edit).
Evidencehttps://github.com/cocktailpeanut/jevthoven/blob/main/app/scripts/live-smoke.mjs#L15
Labelscall-site-verified
codaaiteam/jev-mcp
README states: Official TypeSafe: get a key at console.typesafe.ai. It's used against api.typesafe.ai by default.
Evidencehttps://github.com/codaaiteam/jev-mcp/blob/main/README.md#L30
Labelsreadme-claim
Cognipeer/agent-sdk
README states: Against the real Jev API
Evidencehttps://github.com/Cognipeer/agent-sdk/blob/main/examples/jev-guardrail/README.md#L24
Labelsreadme-claim
colliber/duckdb-jev
README states: the extension talking to api.typesafe.ai.
Evidencehttps://github.com/colliber/duckdb-jev/blob/main/docs/README.md#L4
Labelsreadme-claim
columnar-tech/jevaro
README states: A Python batching proxy for Jev that returns
Evidencehttps://github.com/columnar-tech/jevaro/blob/main/README.md#L3
Labelsreadme-claim
compozy/yoshi
README states: Jev judges new context once, above a configurable size gate. Yoshi applies the
Evidencehttps://github.com/compozy/yoshi/blob/main/README.md#L7
Labelsreadme-claim
Contrastive-LM/CLM
README states: It performs on par with Jev across computer-use, gaming and tool-calling
Evidencehttps://github.com/Contrastive-LM/CLM/blob/main/src/clm/__init__.py#L6
Labelscall-site-verified
CorieW/JevTest
README states: To run the same suite using Jev, copy .env.example to .env.local, set TYPESAFE_API_KEY, then run:
Evidencehttps://github.com/CorieW/JevTest/blob/main/src/jev.ts#L122
Labelscall-site-verified
CTNicholas/jev-workflow-builder
README states: Create an account on typesafe.ai
Evidencehttps://github.com/CTNicholas/jev-workflow-builder/blob/main/README.md#L14
Labelsreadme-claim
danielgshea/jev-as-a-judge
README states: This project tests a third option: Jev, TypeSafe AI's System One decision model. We compare Jev with GPT-5.6 Luna, GPT-5.6 Terra, and Claude Sonnet 4.6 on the same fixed agent runs, measuring binary accuracy, score relia
Evidencehttps://github.com/danielgshea/jev-as-a-judge/blob/main/README.md#L5
Labelsreadme-claim
DanRWilloughby/snifftest
README states: judgment rules too, put a TypeSafe key in TYPESAFE_API_KEY and drop
Evidencehttps://github.com/DanRWilloughby/snifftest/blob/main/src/jev.ts#L50
Labelscall-site-verified
danvega/jev-spring-boot-starter
README states: | jev.api-key | TYPESAFE_API_KEY fallback | TypeSafe API key |
Evidencehttps://github.com/danvega/jev-spring-boot-starter/blob/main/README.md#L145
Labelsreadme-claim
Das-rebel/a3m-router
README states: model="jev-auto" — ML decision head, calibrated probabilities, ~2ms warm
Evidencehttps://github.com/Das-rebel/a3m-router/blob/main/README.md#L120
Labelsreadme-claim
daseinlabs/open-jev
README states: make systemone # TypeSafe-style request against /v1/systemone
Evidencehttps://github.com/daseinlabs/open-jev/blob/main/demo/doom/client.py#L66
Labelscall-site-verified
davila7/jev-explained
README states: Learn how TypeSafe's Jev makes typed, probabilistic decisions — by running it.
Evidencehttps://github.com/davila7/jev-explained/blob/main/src/lib/providers.ts#L21
Labelscall-site-verified
DECRUX9812/typesafe-skill-router
README states: A TypeSafe API key (TYPESAFE_API_KEY) — create one at
Evidencehttps://github.com/DECRUX9812/typesafe-skill-router/blob/main/__init__.py#L30
Labelscall-site-verified
delexw/claude-code-trace
README states: Jev and provider API keys live in the OS credential store (macOS Keychain, Windows Credential
Evidencehttps://github.com/delexw/claude-code-trace/blob/main/src-tauri/src/efficiency/jev.rs#L12
Labelscall-site-verified
dengyie/ai-register-machine
README states: | typesafe.ai / jev | ./register.sh typesafe [count] [threads] | Python + requests + Stytch Magic-Link | typesafe-*.json (0600 API Key) |
Evidencehttps://github.com/dengyie/ai-register-machine/blob/main/README.md#L36
Labelsreadme-claim
devagrawal09/jev-review
README states: The reviewer keeps orchestration in code and uses Jev for bounded judgments:
Evidencehttps://github.com/devagrawal09/jev-review/blob/main/src/review/codebase-judgments.ts#L3
Labelscall-site-verified
devagrawal09/stanley-code
README states: For built-ins, Jev answers fixed-choice questions about each piece. Using your required TypeSafe API key,
Evidencehttps://github.com/devagrawal09/stanley-code/blob/main/README.md#L94
Labelsreadme-claim
Devin-AXIS/jev-dsh-decision
README states: 问题类型是 choice（单选）、score（等级评分）、noul（是的概率）。多个互补 Skill 可使用多个独立 noul 问题。传入最小必要上下文，不传密钥或无关私密资料。网络固定发往 https://api.typesafe.ai/v1/systemone；默认模型 jev-latest。
Evidencehttps://github.com/Devin-AXIS/jev-dsh-decision/blob/main/README.md#L137
Labelsreadme-claim
DevMortimer/pi-warden
README states: Jev requests cost money, so each 1.0 change was measured by what it saves. Each figure is the measured change on recorded sessions of one machine, not a promise for yours.
Evidencehttps://github.com/DevMortimer/pi-warden/blob/main/scripts/slop-cases.mjs#L77
Labelscall-site-verified
devtooligan/jevscan-evm
README states: Produce a heat map of likely bugs - in seconds, for pennies - built with TypeSafe's Jev.
Evidencehttps://github.com/devtooligan/jevscan-evm/blob/main/README.md#L10
Labelsreadme-claim
dfinke/Jev
README states:
Evidencehttps://github.com/dfinke/Jev/blob/main/README.md#L2
Labelsreadme-claim
Dicklesworthstone/skillranker
README states: The right skill for the next step, powered by Jev-compatible providers.
Evidencehttps://github.com/Dicklesworthstone/skillranker/blob/main/src/jev/client/tests.rs#L100
Labelscall-site-verified
Dimweaker/jev-libero
README states:
Evidencehttps://github.com/Dimweaker/jev-libero/blob/main/src/jev_libero/client.py#L14
Labelscall-site-verified
docxology/daf-jev
README states: Modular, composable Python client and decision toolkit for the TypeSafe Jev
Evidencehttps://github.com/docxology/daf-jev/blob/main/src/daf_jev/__init__.py#L23
Labelscall-site-verified
doeixd/discern
README states: error. Provider-neutral: runs on TypeSafe's Jev, or any other DecisionModel.
Evidencehttps://github.com/doeixd/discern/blob/main/README.md#L7
Labelsreadme-claim
dominicrico/jev-router
README states: | jev (default) | https://api.typesafe.ai/v1/systemone | jev-latest | TYPESAFE_API_KEY or /jev key (required) |
Evidencehttps://github.com/dominicrico/jev-router/blob/main/README.md#L94
Labelsreadme-claim
donvito/ai-backends
README states: | TypeSafe Jev | System One decision model: choice, score, and noul questions | Available |
Evidencehttps://github.com/donvito/ai-backends/blob/main/README.md#L99
Labelsreadme-claim
dorkitude/webctl
README states: Smart web search CLI for agents, backed by Jev. Saves a lot of tokens.
Evidencehttps://github.com/dorkitude/webctl/blob/main/README.md#L3
Labelsreadme-claim
Dujaydis/JevSysUno
README states: A reference integration for TypeSafe AI's Jev, the first "System One" model: typed
Evidencehttps://github.com/Dujaydis/JevSysUno/blob/master/README.md#L3
Labelsreadme-claim
ellistev/typesafe-minecraft-demo
README states: An experimental Minecraft Java bot controlled through TypeSafe choices, with a live world view and the actual API input and output beside it.
Evidencehttps://github.com/ellistev/typesafe-minecraft-demo/blob/main/src/decisions.cjs#L45
Labelscall-site-verified
equationalapplications/system-one-reviewer
README states: | jev | --provider jev (default; SOR_PROVIDER env also works) | hosted TypeSafe System One, TYPESAFE_API_KEY | live-tested (all published numbers) |
Evidencehttps://github.com/equationalapplications/system-one-reviewer/blob/main/README.md#L236
Labelsreadme-claim
eriestra/browser-use-olympics
README states: echo 'TYPESAFE_API_KEY=...' > ~/.config/typesafe/env # chmod 600
Evidencehttps://github.com/eriestra/browser-use-olympics/blob/main/almond-fastloop.mjs#L102
Labelscall-site-verified
Eriskii/ErisLint
README states: anything useful, then map Jev's answers to warnings or errors.
Evidencehttps://github.com/Eriskii/ErisLint/blob/main/src/jev.rs#L24
Labelscall-site-verified
EthanAlgoX/AIStock
README states: Try JEV decisions (optional): configure its separate TypeSafe API key in Settings → Models & runtime, then select JEV · Decisions only for a new trading strategy. JEV returns buy/sell/hold, probabilities, and confidence
Evidencehttps://github.com/EthanAlgoX/AIStock/blob/main/README.md#L148
Labelsreadme-claim
etweisberg/jev-ui
README states:
Evidencehttps://github.com/etweisberg/jev-ui/blob/main/apps/demo/scripts/check-key.mjs#L5
Labelscall-site-verified
EugeneBoondock/jevsql
README states:
Evidencehttps://github.com/EugeneBoondock/jevsql/blob/main/src/client.mjs#L28
Labelscall-site-verified
evoke-build/evoke
README states: To decide against Jev, export TYPESAFE_API_KEY for the jev adapter, or OPENJEV_API_KEY for openjev. To
Evidencehttps://github.com/evoke-build/evoke/blob/main/crates/evoke-adapters/src/systemone.rs#L85
Labelscall-site-verified
f-tiger/jev-decision-gate
README states: Use Jev for Issue triage without building the whole integration and review workflow.
Evidencehttps://github.com/f-tiger/jev-decision-gate/blob/main/skills/jev-decision-gate/scripts/jev_decision_gate/triage.py#L15
Labelscall-site-verified
f/jev-leftpad
README states: Set TYPESAFE_API_KEY before using it. jev-leftpad uses jev-latest through
Evidencehttps://github.com/f/jev-leftpad/blob/main/src/index.js#L1
Labelscall-site-verified
fabricioctelles/skills
README states: references/jev-integration.md — integration patterns and code examples
Evidencehttps://github.com/fabricioctelles/skills/blob/main/README.md#L49
Labelsreadme-claim
FBddcz/embodied-jev
README states: 🧠 模型入口放在界面里：可接 TypeSafe Jev、Claude 原生 API、OpenAI 兼容 API，以及本地 MiniCPM5-2B。
Evidencehttps://github.com/FBddcz/embodied-jev/blob/main/README.md#L42
Labelsreadme-claim
featherless-ai/simple-jev
README states: curl https://simple-jev-demo-api.featherless.ai/v1/models
Evidencehttps://github.com/featherless-ai/simple-jev/blob/main/README.md#L20
Labelsreadme-claim
feder-cr/jev
README states:
Evidencehttps://github.com/feder-cr/jev/blob/main/src/main.cpp#L166
Labelscall-site-verified
FeiLiuEM/tetrajev
README states: Four readings. One routed decision. Two frozen open-weight models, four independent readings per task, one fit-free decision layer — Jev-class decision behaviour with no fine-tuning and no distillation.
Evidencehttps://github.com/FeiLiuEM/tetrajev/blob/main/scripts/run_jev_api.py#L5
Labelscall-site-verified
FerryCorleone/crush-monitor
README states: 一个分析你和 Crush 或对象聊天的小工具，支持 Jev、OpenAI Decisions（测试版）和常见文本大模型。帮你读懂一点对方的情绪和想法，也看看自己的回复哪里没表达好、可以怎么调整。
Evidencehttps://github.com/FerryCorleone/crush-monitor/blob/main/server/analysis.ts#L7
Labelscall-site-verified
flitsinc/go-llms
README states: TypeSafe System One models (Jev): typed judgments with probabilities, driven by a JSON output schema
Evidencehttps://github.com/flitsinc/go-llms/blob/main/README.md#L9
Labelsreadme-claim
FluidInference/FluidUse
README states: Jev-style decision model: a 322M mmBERT encoder plus decision head that answers typed
Evidencehttps://github.com/FluidInference/FluidUse/blob/main/Sources/FluidUse/PublishedCoreML/PublishedCoreMLTypes.swift#L80
Labelscall-site-verified
Foadsf/jev-for-engineers
README states: so twelve questions in one call cost about what one call costs. TypeSafe
Evidencehttps://github.com/Foadsf/jev-for-engineers/blob/main/jev.py#L11
Labelscall-site-verified
FrancoisChastel/jev-code
README states: jev-code
Evidencehttps://github.com/FrancoisChastel/jev-code/blob/main/README.md#L1
Labelsreadme-claim
freepik-company/jev-mcp
README states: TypeSafe's System One model, through OpenRouter or TypeSafe directly.
Evidencehttps://github.com/freepik-company/jev-mcp/blob/main/internal/judgment/tasks.go#L35
Labelscall-site-verified
frostney/clean-code-review
README states: Point it at a public GitHub pull request, a diff or a file. Jev, TypeSafe's
Evidencehttps://github.com/frostney/clean-code-review/blob/main/README.md#L7
Labelsreadme-claim
gamesonrblx/Jevbridge
README states: ACP and MCP adapter that bridges TypeSafe Jev with any LLM.
Evidencehttps://github.com/gamesonrblx/Jevbridge/blob/main/src/types.ts#L111
Labelscall-site-verified
gbh1234/Adaptive-rag
README states: INTENT_BACKEND=jev
Evidencehttps://github.com/gbh1234/Adaptive-rag/blob/main/README.md#L83
Labelsreadme-claim
genspark-ai/genoffice
README states: Six apps, one AI panel, a file search reranked by TypeSafe Jev, an Ask AI
Evidencehttps://github.com/genspark-ai/genoffice/blob/main/apps/shell/src/main/file-index/decider.ts#L52
Labelscall-site-verified
get-convex/convex-evals
README states: bun run decisions dry-run --provider openrouter --model typesafe/jev-1.13 --limit-evals 2
Evidencehttps://github.com/get-convex/convex-evals/blob/main/README.md#L44
Labelsreadme-claim
GhalebDweikat/winnow
README states: winnow replay score --judged ~/.winnow/replay/judged-typesafe.jsonl
Evidencehttps://github.com/GhalebDweikat/winnow/blob/main/sidecar/src/winnow/hooks.py#L282
Labelscall-site-verified
GhrezaKh74/JevTicktRouter
README states: Structured support-ticket triage built on .NET 10 and React 19, using TypeSafe Jev to make
Evidencehttps://github.com/GhrezaKh74/JevTicktRouter/blob/master/backend/JevTicketRouter.Infrastructure/Decisions/SelfHosted/SelfHostedOptions.cs#L42
Labelscall-site-verified
gi-dellav/hsom
README states: hsom* is a strict-allowlist harness. environment.toml defines which shell commands Jev (the TypeSafe System One classifier) may select. In one step, Jev picks: command → subcommand → flags (boolean or valued) → path slot
Evidencehttps://github.com/gi-dellav/hsom/blob/main/README.md#L5
Labelsreadme-claim
githubnext/localjev
README states: A local, Jev-compatible POST /v1/systemone API written in TypeScript for
Evidencehttps://github.com/githubnext/localjev/blob/main/src/server.ts#L19
Labelscall-site-verified
Godefroy/micdrop
README states: @micdrop/typesafe - Jev, the System One model of TypeSafe, classifying each turn of the user into typed decisions in a few hundred ms
Evidencehttps://github.com/Godefroy/micdrop/blob/main/README.md#L27
Labelsreadme-claim
GodsBoy/jev-agent-skill-router
README states:
Evidencehttps://github.com/GodsBoy/jev-agent-skill-router/blob/main/src/jev_router/transport.py#L12
Labelscall-site-verified
gopaljigaur/decide
README states: them through one API: TypeSafe's hosted Jev, OpenRouter, OpenAI's Decisions
Evidencehttps://github.com/gopaljigaur/decide/blob/main/decide/backends/typesafe.py#L20
Labelscall-site-verified
Govcraft/emergent
README states: Judgment as a Pipeline Step: jev-handler
Evidencehttps://github.com/Govcraft/emergent/blob/main/README.md#L161
Labelsreadme-claim
gtaras7/typesafe-jev
README states: A local screening workbench for a folder of CVs, built on TypeSafe's Jev model. Point it at one CV or
Evidencehttps://github.com/gtaras7/typesafe-jev/blob/main/cv-screen/src/cli.ts#L97
Labelscall-site-verified
GuSheng107/helpme-Jev
README states: JEV decides. LLM explains. You decide.
Evidencehttps://github.com/GuSheng107/helpme-Jev/blob/main/README.md#L55
Labelsreadme-claim
hamgua/alpha-trading-bot-okx
README states: Jev 快车道（TypeSafe System One）
Evidencehttps://github.com/hamgua/alpha-trading-bot-okx/blob/main/README.md#L361
Labelsreadme-claim
harlan-zw/harlan-agent-kit
README states: api.typesafe.ai or the Vercel AI Gateway.
Evidencehttps://github.com/harlan-zw/harlan-agent-kit/blob/main/packages/advocaat/README.md#L9
Labelsreadme-claim
haseeb-heaven/jev-system-one
README states: A polished terminal interface where OpenAI generates useful answers and TypeSafe Jev independently evaluates their relevance, reliability, and quality.
Evidencehttps://github.com/haseeb-heaven/jev-system-one/blob/master/src/jev_system_one/jev.py#L3
Labelscall-site-verified
hatt-io/jevkeep
README states: Before compaction, JevKeep reads the conversation and asks Jev, a relevance-scoring model accessed through the Typesafe API, which excerpts still matter to the current task.
Evidencehttps://github.com/hatt-io/jevkeep/blob/main/README.md#L17
Labelsreadme-claim
hellogumbo/should-ai-kill-us-all
README states: We ask Jev, TypeSafe AI's System One model, whether AI should kill us all. Every ten minutes. Using the actual headlines.
Evidencehttps://github.com/hellogumbo/should-ai-kill-us-all/blob/main/functions/api/verdict.js#L10
Labelscall-site-verified
hellozenstrategist-lab/eutrya
README states: A standalone terminal agent with Jev in its decision loop.
Evidencehttps://github.com/hellozenstrategist-lab/eutrya/blob/main/extensions/eutrya-adaptive-extension/integration/native-v02.mjs#L9
Labelscall-site-verified
hemanth/is-lesion
README states: jev — TypeSafe System One (jev-1.14.0) with 1 Hugging Face visual reference exemplar per class (noul + choice + score + box)
Evidencehttps://github.com/hemanth/is-lesion/blob/main/README.md#L48
Labelsreadme-claim
hev/reranker
README states: nDCG@10, every system permuting the same BM25 top-30 shortlist per query. Jev uses the
Evidencehttps://github.com/hev/reranker/blob/main/hev_rerank/rerank.py#L18
Labelscall-site-verified
heyjunpenn/awesome-jev
README states: | openai-scala-client | ★ 249 | Scala | 2026-09-23 | Scala client module for TypeSafe System One that submits Jev Noul, Choice, and Score questions and returns typed answers. |
Evidencehttps://github.com/heyjunpenn/awesome-jev/blob/main/README.md#L80
Labelsreadme-claim
HorusJiang/dsh-jev-tools
README states: 一个 DeepSeek Harness 插件：把 Jev 接进长会话，在工具结果进入上下文之前做判定。
Evidencehttps://github.com/HorusJiang/dsh-jev-tools/blob/main/README.md#L18
Labelsreadme-claim
hotchpotch/jev-reranker
README states: | model | Explicit value → JEV_MODEL (environment/.env) → jev-latest |
Evidencehttps://github.com/hotchpotch/jev-reranker/blob/main/README.md#L434
Labelsreadme-claim
hraness/algal
README states: or reuse a TypeSafe key. doctor --clef checks configuration without an API
Evidencehttps://github.com/hraness/algal/blob/main/README.md#L895
Labelsreadme-claim
hunkim/solar-mini4-jev
README states: A drop-in wrapper that exposes Upstage Solar Pro4 (default; solar-mini4 optional) through the TypeSafe Jev System One API shape.
Evidencehttps://github.com/hunkim/solar-mini4-jev/blob/main/engine.py#L158
Labelscall-site-verified
huntedman/JevLint
README states: JevLint is powered by Jev, TypeSafe AI’s System One model. It sends selected source
Evidencehttps://github.com/huntedman/JevLint/blob/main/src/jev-client.ts#L52
Labelscall-site-verified
HyunjunJeon/jev-judgment
README states: TypeSafe Jev and acts on the probabilities. The
Evidencehttps://github.com/HyunjunJeon/jev-judgment/blob/main/README.md#L6
Labelsreadme-claim
iamjonatha/decisionkit-dotnet
README states: A strongly typed, provider-independent decision engine for .NET, with TypeSafe JEV support.
Evidencehttps://github.com/iamjonatha/decisionkit-dotnet/blob/main/README.md#L3
Labelsreadme-claim
iamtoomas/JevLint
README states: JevLint is powered by Jev, TypeSafe AI’s System One model. It sends selected source
Evidencehttps://github.com/iamtoomas/JevLint/blob/main/src/jev-client.ts#L52
Labelscall-site-verified
IAmUnbounded/save-token-jev-clean
README states: | TYPESAFE_API_KEY | required unless stored in the macOS Keychain (CLI and library only) | TypeSafe/Jev API key |
Evidencehttps://github.com/IAmUnbounded/save-token-jev-clean/blob/main/README.md#L185
Labelsreadme-claim
iamvatsalpatel/tiershift
README states: The judgment comes from TypeSafe Jev , a calibrated decision model. About 180 ms. Four cents per thousand routes.
Evidencehttps://github.com/iamvatsalpatel/tiershift/blob/main/bench/experiments/gate-experiment.ts#L10
Labelscall-site-verified
iefnaf/pi-jev
README states:
Evidencehttps://github.com/iefnaf/pi-jev/blob/main/README.md#L9
Labelsreadme-claim
ielab/llm-rankers
README states: : New experiments with Jev (TypeSafe AI's non-generative "System One" model) as a pointwise / pairwise / setwise / listwise reranker, including all 100 candidates in a single request. Check out the jev folder for results
Evidencehttps://github.com/ielab/llm-rankers/blob/main/README.md#L7
Labelsreadme-claim
ilyamk/jev-gmail-ai-spam-filter-and-labeling
README states: Semantic email classification powered by Jev, with confidence-aware automation,
Evidencehttps://github.com/ilyamk/jev-gmail-ai-spam-filter-and-labeling/blob/main/README.md#L11
Labelsreadme-claim
InternLM/Intern-Decision
README states: Intern-Decision-4B reaches 90.02% average accuracy across seven suites (Jev: 88.74%),
Evidencehttps://github.com/InternLM/Intern-Decision/blob/main/README.md#L97
Labelsreadme-claim
intikhab49/open-jev-typed-decision-engine
README states:
Evidencehttps://github.com/intikhab49/open-jev-typed-decision-engine/blob/main/README.md#L3
Labelsreadme-claim
ipenywis/laya-ultrafast
README states: Hosted mode still works. Set DECISION_MODEL=typesafe to use the original Jev policy unchanged.
Evidencehttps://github.com/ipenywis/laya-ultrafast/blob/main/laya_ultrafast/laya.py#L48
Labelscall-site-verified
ItIsCuthNotCup/MetaCog
README states: judge = SystemOneJudge.jev() # hosted; reads $TYPESAFE_API_KEY
Evidencehttps://github.com/ItIsCuthNotCup/MetaCog/blob/main/README.md#L48
Labelsreadme-claim
itsmostafa/typesafe-mcp
README states: Give your AI agent direct access to models like TypeSafe Jev, Liquid AI d1, Cloudflare Clef, Respan Span-01, GPT-6 Luna Decisions, and Perplexity Decider Flash: quick decisions with real probabilities.
Evidencehttps://github.com/itsmostafa/typesafe-mcp/blob/main/README.md#L10
Labelsreadme-claim
itsoltech/basal-rs
README states:
Evidencehttps://github.com/itsoltech/basal-rs/blob/main/contracts/typesafe/README.md#L4
Labelsreadme-claim
j1s4nn/duomind
README states: Internet connection for setup and Jev API calls
Evidencehttps://github.com/j1s4nn/duomind/blob/main/README.md#L111
Labelsreadme-claim
JamesANZ/us-legal-mcp
README states: JEV_MODEL – default jev-latest
Evidencehttps://github.com/JamesANZ/us-legal-mcp/blob/main/README.md#L234
Labelsreadme-claim
jamesward/zio-typesafe-ai
README states: Jev / System One API — a "System One model" that answers typed, atomic
Evidencehttps://github.com/jamesward/zio-typesafe-ai/blob/main/src/main/scala/com/jamesward/zio_typesafe_ai/TypeSafeAI.scala#L3
Labelscall-site-verified
JanOstrowka/typesafe-assist
README states:
Evidencehttps://github.com/JanOstrowka/typesafe-assist/blob/main/custom_components/typesafe_conversation/api.py#L161
Labelscall-site-verified
jaredpalmer/kev
README states: Small Jev-like decision models you can train and run yourself.
Evidencehttps://github.com/jaredpalmer/kev/blob/main/README.md#L3
Labelsreadme-claim
jarrodwatts/jev-trader
README states: With no PRIVATE_KEY it dry-runs: real book, real decisions, simulated fills. Set MODEL=jev and TYPESAFE_AI_API_KEY to use Jev; the default mock is a momentum heuristic stand-in.
Evidencehttps://github.com/jarrodwatts/jev-trader/blob/main/src/model.ts#L2
Labelscall-site-verified
jccrump/openbot
README states: Google, Mistral, or a local model through Ollama or LM Studio. An optional Jev
Evidencehttps://github.com/jccrump/openbot/blob/main/README.md#L7
Labelsreadme-claim
jcpsimmons/jev-macos-loop
README states: Read https://raw.githubusercontent.com/jcpsimmons/jev-macos-loop/master/AGENTS.md
Evidencehttps://github.com/jcpsimmons/jev-macos-loop/blob/master/src/providers.mjs#L17
Labelscall-site-verified
JedimEmO/typesafe-client
README states: endorsed by, or supported by TypeSafe AI. For the API itself, see the
Evidencehttps://github.com/JedimEmO/typesafe-client/blob/main/crates/typesafe-client/src/answer.rs#L405
Labelscall-site-verified
jerryfane/omp-jev-compaction
README states: TypeSafe's Jev decision model, over either the TypeSafe API or OpenRouter.
Evidencehttps://github.com/jerryfane/omp-jev-compaction/blob/master/src/asker.ts#L21
Labelscall-site-verified
jev-chat/jev-chat-windows
README states: 判断 · Jev —— 判断意图、紧张度，并给三条候选排序。来源选 OpenRouter（默认，key 在
Evidencehttps://github.com/jev-chat/jev-chat-windows/blob/main/README.md#L47
Labelsreadme-claim
jhd3197/Prompture
README states: driver = get_decision_driver_for_model("typesafe/jev-latest")
Evidencehttps://github.com/jhd3197/Prompture/blob/main/prompture/drivers/kev_decision_driver.py#L4
Labelscall-site-verified
jkudish/jev-mcp
README states: Jev is TypeSafe's System One model: it returns typed answers with calibrated probability distributions, not generated text. A verify call is a Choice over supports / contradicts / says_nothing, so you see the whole distr
Evidencehttps://github.com/jkudish/jev-mcp/blob/main/README.md#L733
Labelsreadme-claim
jmanhype/jev-dspy-lab
README states: and other callers that use TypeSafe decisions inside DSPy-style pipelines.
Evidencehttps://github.com/jmanhype/jev-dspy-lab/blob/main/scripts/verify_integration.py#L41
Labelscall-site-verified
joelhooks/pi-fast-jev-compaction
README states: Sends a compact representation of tool calls and surrounding conversation to TypeSafe's /v1/systemone endpoint.
Evidencehttps://github.com/joelhooks/pi-fast-jev-compaction/blob/main/src/core/request.ts#L8
Labelscall-site-verified
jomatsu/pi-jev-auto-mode
README states: decision models, with Jev (TypeSafe System One) as the default. OpenAI Decisions,
Evidencehttps://github.com/jomatsu/pi-jev-auto-mode/blob/main/src/jev/engine.ts#L95
Labelscall-site-verified
jomatsu/zod-jev
README states: A single parseAsync call sends every rule of that schema to Jev in a single request, then turns
Evidencehttps://github.com/jomatsu/zod-jev/blob/main/scripts/check-package.mjs#L35
Labelscall-site-verified
jonathanavis96/jev-kit
README states: What is Jev, and why a kit
Evidencehttps://github.com/jonathanavis96/jev-kit/blob/main/README.md#L39
Labelsreadme-claim
jozefRudy/job_search
README states: Optional; omit either key to use the default (https://api.typesafe.ai, jev-latest).
Evidencehttps://github.com/jozefRudy/job_search/blob/main/README.md#L52
Labelsreadme-claim
jucelioalencar/linearmemory
README states: Contracts: OpenAI Decisions and TypeSafe System One. Settings are available at GET/PUT /api/settings/search-filter; existing search snapshots are returned by GET /api/search-results/:eventId without rerunning retrieval.
Evidencehttps://github.com/jucelioalencar/linearmemory/blob/main/README.md#L175
Labelsreadme-claim
jujumilk3/jev-calibration-audit
README states: An independent, API-only audit of the calibration of TypeSafe AI's Jev, a
Evidencehttps://github.com/jujumilk3/jev-calibration-audit/blob/main/src/jev_audit/client.py#L12
Labelscall-site-verified
justinhe16/trade-jev
README states: Run: a backtest that calls Jev and stores its answers and trades in runs/ /. It's the only step that costs money.
Evidencehttps://github.com/justinhe16/trade-jev/blob/main/src/trade_jev/live.py#L993
Labelscall-site-verified
jxucoder/mimicry
README states: and TypeSafe; requests and responses are saved locally under ignored
Evidencehttps://github.com/jxucoder/mimicry/blob/master/README.md#L37
Labelsreadme-claim
kavehmz/typesafe-playground
README states: Small, interactive experiments with TypeSafe Jev: from understanding a support message to making decisions for a car in a 3D world.
Evidencehttps://github.com/kavehmz/typesafe-playground/blob/main/demo01/server.mjs#L67
Labelscall-site-verified
keltokhy/jgrep
README states: Each line becomes one yes/no question to Jev, TypeSafe's decision
Evidencehttps://github.com/keltokhy/jgrep/blob/main/README.md#L16
Labelsreadme-claim
kesku/jev-freeform
README states: Can TypeSafe Jev Choice generate text through successive typed decisions? Well I tried it
Evidencehttps://github.com/kesku/jev-freeform/blob/main/main.mjs#L172
Labelscall-site-verified
kevinbadi/jev-voice
README states: Everything runs locally except one ~250 ms call to Jev (TypeSafe's System One
Evidencehttps://github.com/kevinbadi/jev-voice/blob/main/jev_voice/brain.py#L174
Labelscall-site-verified
Kevthetech143/super-jev
README states: One judge sits between your agent and your data: the agent asks in its own words, Jev finds the file, checks the claim, permits the action, and remembers what you approved. Your agent stays responsible for the answer.
Evidencehttps://github.com/Kevthetech143/super-jev/blob/main/README.md#L9
Labelsreadme-claim
kieranklaassen/ruby_llm-typesafe
README states: Both register a provider named :typesafe, so don't load both. When you upgrade, remove ruby_llm-typesafe from your Gemfile and use RubyLLM's built-in provider.
Evidencehttps://github.com/kieranklaassen/ruby_llm-typesafe/blob/main/README.md#L11
Labelsreadme-claim
KiritoKing/midscene-jev-runner
README states: The default is TypeSafe System One: POST https://api.typesafe.ai/v1/systemone
Evidencehttps://github.com/KiritoKing/midscene-jev-runner/blob/main/README.md#L66
Labelsreadme-claim
klauswg/jev-guard
README states: Real-time risk triage gateway for crypto exchange deposits & withdrawals — Jev (TypeSafe System One) as the triage layer, deterministic code as the judge.
Evidencehttps://github.com/klauswg/jev-guard/blob/master/src/main/java/com/jevguard/client/JevClient.java#L13
Labelscall-site-verified
klauswg/jev-suite
README states: Four decision-quality tools built on Jev (TypeSafe System One), one shared kernel — Jev answers structured questions; deterministic code keeps the final say.
Evidencehttps://github.com/klauswg/jev-suite/blob/master/jev-fidelity/src/main/java/com/jevsuite/fidelity/eval/EvalRunner.java#L52
Labelscall-site-verified
knowlet/jevlens
README states: Manifest V3 Chrome extension for annotating articles, X/Twitter posts, and Threads posts with typed Jev / System One decisions.
Evidencehttps://github.com/knowlet/jevlens/blob/master/extension/lib/jev.js#L4
Labelscall-site-verified
kouhxp/gutsy
README states: network calls, no per-call cost. The API follows the Jev-style Decisions format, so existing clients
Evidencehttps://github.com/kouhxp/gutsy/blob/main/gutsy-inference/gutsy_inference/server.py#L21
Labelscall-site-verified
kraayenjon/awesome-jev
README states:
Evidencehttps://github.com/kraayenjon/awesome-jev/blob/main/README.md#L2
Labelsreadme-claim
kshetrajna12/reflex
README states: the "System One" model TypeSafe released in September 2026, built on top of a normal
Evidencehttps://github.com/kshetrajna12/reflex/blob/main/scripts/bench_latency.py#L6
Labelscall-site-verified
kyegomez/open-jev
README states: System One Models and Jev
Evidencehttps://github.com/kyegomez/open-jev/blob/main/README.md#L161
Labelsreadme-claim
kyu1204/jgrep
README states: jgrep runs on Jev, through TypeSafe or
Evidencehttps://github.com/kyu1204/jgrep/blob/main/README.md#L41
Labelsreadme-claim
kyu1204/oh-my-harness
README states: --preset always wins and never calls Jev. No key and no LLM provider? omh init "description" falls back to safe and says so.
Evidencehttps://github.com/kyu1204/oh-my-harness/blob/main/src/catalog/blocks/semantic-rule-guard.ts#L68
Labelscall-site-verified
lakeday-org/perch
README states: export PERCH_BASE_URL=https://api.typesafe.ai/v1/systemone
Evidencehttps://github.com/lakeday-org/perch/blob/main/.benchmarks/reviewbench/run.mjs#L15
Labelscall-site-verified
lhotwll217/jev-cli
README states: JSON in, typed decisions out. A thin CLI over the TypeSafe System One API
Evidencehttps://github.com/lhotwll217/jev-cli/blob/main/src/client.ts#L25
Labelscall-site-verified
Li-Evan/awesome-jev
README states: http4k TypeSafe connector - TypeSafe connector for the http4k Kotlin toolkit with a typed System One client and a fake, exposing Jev Noul, Choice and Score questions as http4k actions.
Evidencehttps://github.com/Li-Evan/awesome-jev/blob/main/README.md#L468
Labelsreadme-claim
libingzheren/Jev-Mem
README states: Jev-Mem separates the frequent decisions of memory management from the deeper
Evidencehttps://github.com/libingzheren/Jev-Mem/blob/main/memory/jev_client.py#L23
Labelscall-site-verified
liu-x27/XavierJev
README states: TypeSafe: nothing here calls the Jev API, and nothing was trained on its output.
Evidencehttps://github.com/liu-x27/XavierJev/blob/main/eval/decision-models/run.ts#L177
Labelscall-site-verified
liuyanghejerry/Clausura
README states: model: jev-latest # Default. Decision model id.
Evidencehttps://github.com/liuyanghejerry/Clausura/blob/main/README.md#L330
Labelsreadme-claim
luisleo526/doc2mark
README states: TypeSafe's Jev can be asked about the cases they leave open (is this
Evidencehttps://github.com/luisleo526/doc2mark/blob/main/README.md#L23
Labelsreadme-claim
lykycy123/RoboJEV
README states: Two-stage JEV control of a Franka Panda in MuJoCo. Measured simulator state → task intent → Cartesian motion and gripper commands.
Evidencehttps://github.com/lykycy123/RoboJEV/blob/main/src/jev_vla_sim/config.py#L27
Labelscall-site-verified
lyramakesmusic/jevbot
README states: Completeness judge: A separate noul question asks "is the reply complete?" — jev stops when it thinks it's done
Evidencehttps://github.com/lyramakesmusic/jevbot/blob/master/README.md#L11
Labelsreadme-claim
maayanlevy/mysql-ailike
README states: Requires a TypeSafe API key. Note: evaluated values and prompts are
Evidencehttps://github.com/maayanlevy/mysql-ailike/blob/main/src/typesafe.h#L16
Labelscall-site-verified
madisonrickert/jev-permission-gate
README states: A shell-aware blocklist sits in front of Jev. A call it flags can still be denied by Jev but is never allowed, and a call that carries a secret never leaves your machine.
Evidencehttps://github.com/madisonrickert/jev-permission-gate/blob/main/hooks/register.ts#L25
Labelscall-site-verified
MahmoudAdelbghany/jev-browser
README states: one Jev call (parallel questions, ~300 ms, no LLM tokens)
Evidencehttps://github.com/MahmoudAdelbghany/jev-browser/blob/main/src/jev.mjs#L1
Labelscall-site-verified
mahynotch/newsscore
README states: News sentiment scoring for stocks, powered by TypeSafe Jev by default. Mainstream financial news APIs go in, a pluggable
Evidencehttps://github.com/mahynotch/newsscore/blob/main/src/newsscore/scoring/jev.py#L416
Labelscall-site-verified
maker-KK/todo-jev
README states: A task-routing experiment powered by TypeSafe Jev, structured skill profiles, and basic environment checks.
Evidencehttps://github.com/maker-KK/todo-jev/blob/main/app/classifier.py#L14
Labelscall-site-verified
malDuffin/typesafe-3d-chess
README states: D chess powered by TypeSafe AI (Jev). AI vs AI by default, or play either side. Multiple difficulty levels.
Evidencehttps://github.com/malDuffin/typesafe-3d-chess/blob/main/README.md#L2
Labelsreadme-claim
mandu5/jevcompat
README states: About a hundred servers say they are "Jev-compatible". Nothing said what that means. Now something does.
Evidencehttps://github.com/mandu5/jevcompat/blob/main/README.md#L3
Labelsreadme-claim
manifoldor/xtags
README states: 页面文本会发送到所选 API 服务（默认 TypeSafe）做判断——这是它工作的必要部分。发送的是帖子正文和作者 handle；折叠长推文会发送 X 页面数据中已有的全文，即使你尚未点击展开。
Evidencehttps://github.com/manifoldor/xtags/blob/main/extension/service.js#L3
Labelscall-site-verified
marcreichel/laya-php
README states: curl -fsSL https://api.typesafe.ai/openapi.json -o openapi.json
Evidencehttps://github.com/marcreichel/laya-php/blob/main/src/Laya.php#L197
Labelscall-site-verified
MarissaFamularo/citation-verifier
README states: supports the sentence, and Jev's confidence in its own call. A probability
Evidencehttps://github.com/MarissaFamularo/citation-verifier/blob/main/README.md#L34
Labelsreadme-claim
markjaquith/typesafe-ai-playground
README states: The experiments live in a Rust CLI called typesafe-ai, built with
Evidencehttps://github.com/markjaquith/typesafe-ai-playground/blob/main/src/typesafe.rs#L57
Labelscall-site-verified
MartinPuli/f1
README states: The engine and experiment scripts remain in the repository. The published interface only plays recorded races; it has no creation or admin screen. Replays use saved decisions and frames without calling TypeSafe.
Evidencehttps://github.com/MartinPuli/f1/blob/main/scripts/refine-prompts.mjs#L55
Labelscall-site-verified
mattn/go-jev
README states: text. Comes with jev-cli, a command-line tool built on it for UNIX pipelines.
Evidencehttps://github.com/mattn/go-jev/blob/main/jev.go#L19
Labelscall-site-verified
mejiasd3v/pi-jev-router
README states:
Evidencehttps://github.com/mejiasd3v/pi-jev-router/blob/main/index.ts#L407
Labelscall-site-verified
memos-im/xianyu-slang-helper
README states: 追加 --ai-review 可用 TypeSafe System One 判别模型（Jev；自托管 DiffusionGemma 同 API）剔除上游的"模板化噪音"变体：每个候选变体问一个 Noul（是/否）问题，取概率 ≥ 阈值判为噪音，不生成文本、无解析、返回校准概率。未配置 key 时自动降级跳过，不阻断同步。
Evidencehttps://github.com/memos-im/xianyu-slang-helper/blob/main/README.md#L147
Labelsreadme-claim
Micha0827/snapjudge
README states: The HTTP API follows the TypeSafe System One format
Evidencehttps://github.com/Micha0827/snapjudge/blob/main/README.md#L7
Labelsreadme-claim
misbahsy/doc-router
README states: Jev (TypeSafe System One) — the page judge. Given the
Evidencehttps://github.com/misbahsy/doc-router/blob/main/README.md#L36
Labelsreadme-claim
mithalouni/system-one-open
README states: Base URL: https://mithalouni--jev-serve-e2b-full-server-web.modal.run (scales to zero; first request after idle takes ~60 s).
Evidencehttps://github.com/mithalouni/system-one-open/blob/main/README.md#L31
Labelsreadme-claim
mizchi/jev-lint
README states: export TYPESAFE_API_KEY=... # https://typesafe.ai
Evidencehttps://github.com/mizchi/jev-lint/blob/main/src/clef.ts#L54
Labelscall-site-verified
mizchi/jev-test-filter
README states: jev-test-filter reads a git diff, asks a model how much that change can
Evidencehttps://github.com/mizchi/jev-test-filter/blob/main/src/jev.ts#L26
Labelscall-site-verified
mkotlikov/jev-grug
README states: The demo now connects to the real Jev API when TYPESAFE_API_KEY is configured. Without a key it falls back to a deterministic mock, so contributors can still run the interface immediately.
Evidencehttps://github.com/mkotlikov/jev-grug/blob/main/app/api/chat/route.ts#L30
Labelscall-site-verified
mmastrac/djev
README states: POST /v1/systemone implements the Jev decision API. The body holds
Evidencehttps://github.com/mmastrac/djev/blob/main/structured_server.py#L2014
Labelscall-site-verified
mmastrac/djev-spark
README states: it implements Jev's POST /v1/systemone API and passes ordinary chat through
Evidencehttps://github.com/mmastrac/djev-spark/blob/main/scripts/long-context-probe.py#L35
Labelscall-site-verified
mohsen1/llm-debugger-vscode-extension
README states: Each step's "what next?" is answered by Jev, a
Evidencehttps://github.com/mohsen1/llm-debugger-vscode-extension/blob/main/README.md#L7
Labelsreadme-claim
morganlinton/Albatross
README states: Jev Mode puts TypeSafe AI's decision model before the main LLM. Supported questions
Evidencehttps://github.com/morganlinton/Albatross/blob/main/src/jev.rs#L13
Labelscall-site-verified
moritzkremb/jev-voice-browser
README states: the server asks Jev (TypeSafe's System One model, jev-1.13.0) one request with a dozen typed
Evidencehttps://github.com/moritzkremb/jev-voice-browser/blob/main/src/jev.js#L7
Labelscall-site-verified
mossyfield/ST-jeved
README states: Jeved is a SillyTavern extension. It sends chat messages to Jev, a small decision model, with
Evidencehttps://github.com/mossyfield/ST-jeved/blob/main/src/classifier.js#L22
Labelscall-site-verified
mrbanana55/Decision_Blackjack
README states: Jev (Remote Cloud AI via TypeSafe System One)
Evidencehttps://github.com/mrbanana55/Decision_Blackjack/blob/main/README.md#L8
Labelsreadme-claim
mrmps/classifier-dev
README states: Both tiers answer from TypeSafe's Jev, a decision
Evidencehttps://github.com/mrmps/classifier-dev/blob/main/README.md#L128
Labelsreadme-claim
n42blockchain/N42-rs
README states: 用户在页面确认费用并提交，页面展示 requestId。运营方建立 job.json，包含下方字段，运行 TYPESAFE_API_KEY=... N42_DECISION_SIGNING_KEY=... cargo run -p n42-decision-relay -- evaluate job.json ./archive > result.json。TYPESAFE_API_URL 默认官方 https://api.typesa
Evidencehttps://github.com/n42blockchain/N42-rs/blob/main/ddn/docs/decision/README.md#L44
Labelsreadme-claim
Nainish-Rai/jev-frontend-qa
README states: Bounded Jev decisions: typed operation/target choices over observed controls; exact fixture values and correctness checks remain in code.
Evidencehttps://github.com/Nainish-Rai/jev-frontend-qa/blob/main/src/jev_frontend_qa/core/model_client.py#L3
Labelscall-site-verified
Nancy-Chauhan/hearth-jev-rental-search
README states: A TypeSafe API key. A search costs a fraction of a cent
Evidencehttps://github.com/Nancy-Chauhan/hearth-jev-rental-search/blob/main/README.md#L18
Labelsreadme-claim
NandhaKishorM/laya
README states: wire protocol as TypeSafe's hosted Jev API. Laya's answer payload is already
Evidencehttps://github.com/NandhaKishorM/laya/blob/main/laya-dotnet/tools/bench_python.py#L191
Labelscall-site-verified
Nasrallah-AL/jev-cli
README states: Fast, typed AI judgments from the command line, powered by TypeSafe's Jev model.
Evidencehttps://github.com/Nasrallah-AL/jev-cli/blob/main/README.md#L8
Labelsreadme-claim
nassim-arifette/jevgrep
README states: authorized repository, asks Jev to score all eligible fragments, then returns the
Evidencehttps://github.com/nassim-arifette/jevgrep/blob/main/experiments/jev-contract/offline-worker.mjs#L4
Labelscall-site-verified
ndolinschi/harnessjudge
README states: After an agent step (paste a trace) → ok / retry / escalate / stop — for agent builders, powered by TypeSafe Jev.
Evidencehttps://github.com/ndolinschi/harnessjudge/blob/main/src/app/api/decide/route.ts#L7
Labelscall-site-verified
ndolinschi/pulselane
README states: Clinic triage decisions powered by TypeSafe Jev (System One).
Evidencehttps://github.com/ndolinschi/pulselane/blob/main/src/app/api/decide/route.ts#L9
Labelscall-site-verified
ndolinschi/toolgate
README states: Agent tool/MCP call gate — paste a planned tool call + context → allow / ask_human / deny with risk scores via TypeSafe Jev.
Evidencehttps://github.com/ndolinschi/toolgate/blob/main/src/app/api/decide/route.ts#L9
Labelscall-site-verified
newfull5/malkuth
README states: suites and about 129,000 questions. Every model answered the same items. Jev was measured through its API.
Evidencehttps://github.com/newfull5/malkuth/blob/main/tools/laya_bench.py#L27
Labelscall-site-verified
NiazMorshed2007/jev-review
README states: Your API key stays on your machine. Jev Review has no hosted backend, database, telemetry service, or author-operated proxy. The only remote request is sent directly to the configured Jev API.
Evidencehttps://github.com/NiazMorshed2007/jev-review/blob/main/src/jev/client.ts#L4
Labelscall-site-verified
nican2018/shade-arena-jev-monitor
README states: Strong per-action gate. Scoring each tool call before it runs, Jev ranked sabotage above almost all benign actions. Gemini Flash's scores piled up at 0 and 100.
Evidencehttps://github.com/nican2018/shade-arena-jev-monitor/blob/main/llms/typesafe_llm.py#L20
Labelscall-site-verified
nicobailon/pi-powerline-footer
README states: When the agent is working, Enter sends your message as steering and Alt+Enter queues it as a follow-up. Set autoFollowUp under powerline to let TypeSafe's Jev make that call for plain Enter:
Evidencehttps://github.com/nicobailon/pi-powerline-footer/blob/main/README.md#L329
Labelsreadme-claim
nicobailon/surf-cli
README states: --allow-semantic - Opt in to bounded model decisions for a semantic workflow (model from SURF_SEMANTIC_MODEL, default jev-1.13.0; extract steps always use clairic with Cloudflare credentials)
Evidencehttps://github.com/nicobailon/surf-cli/blob/main/native/semantic-cli.cjs#L632
Labelscall-site-verified
nidhi-singh02/agent-router
README states: shared accounts), asks TypeSafe to rank what is left and choose an effort, starts the chosen
Evidencehttps://github.com/nidhi-singh02/agent-router/blob/main/packages/router/src/commands/effort.ts#L264
Labelscall-site-verified
Nisaka520/JevIntent
README states: POST https://api.typesafe.ai/v1/systemone：
Evidencehttps://github.com/Nisaka520/JevIntent/blob/main/README.md#L232
Labelsreadme-claim
NobleSpartan6/otto
README states: In Hybrid mode, GPT-6 Astra provides a plan and generated text when needed. Jev chooses concrete actions between planning calls.
Evidencehttps://github.com/NobleSpartan6/otto/blob/main/core/typesafe.ts#L4
Labelscall-site-verified
noetion/dsh-jev
README states: dsh-jev is a DeepSeek Harness bundle that registers the jev_ask tool. A DSH agent on a profile that loads it can send typed noul, choice, and score questions to TypeSafe Jev.
Evidencehttps://github.com/noetion/dsh-jev/blob/main/src/client.ts#L10
Labelscall-site-verified
NorbertBodziony/guard-jev
README states: Text moderation demo: one TypeSafe systemOne call screens 7 Noul hazards + 1 severity Score in parallel. Verdict computed in code via policy thresholds.
Evidencehttps://github.com/NorbertBodziony/guard-jev/blob/main/app/api/moderate/route.ts#L2
Labelscall-site-verified
notque/vexjoy-agent
README states: /d — Jev-Powered Router
Evidencehttps://github.com/notque/vexjoy-agent/blob/main/README.md#L44
Labelsreadme-claim
ntedvs/commentcop
README states: Use --dry-run to preview what it finds without calling Jev. Add exclusions with --ignore or a .commentcopignore file. --help has the rest.
Evidencehttps://github.com/ntedvs/commentcop/blob/main/src/judge.ts#L1
Labelscall-site-verified
Nyarlathoteppppp/pi-heed
README states: messages, 9,090 real tool calls) through pi-heed in enforce mode with Jev, without executing anything
Evidencehttps://github.com/Nyarlathoteppppp/pi-heed/blob/main/src/judge.ts#L53
Labelscall-site-verified
obie/ruby_decision_model
README states: Requests go to https://api.typesafe.ai/v1/systemone. The default model is
Evidencehttps://github.com/obie/ruby_decision_model/blob/main/README.md#L85
Labelsreadme-claim
oficcejo/aiagents-stock
README states: Key 申请：https://console.typesafe.ai ｜完整说明：TypeSafe Jev决策引擎接入说明
Evidencehttps://github.com/oficcejo/aiagents-stock/blob/main/README.md#L170
Labelsreadme-claim
ojusave/beat-jev
README states: A penalty shootout against TypeSafe Jev. Take turns shooting and keeping goal. One Render Workflows task owns the match, with scores saved in Render Postgres.
Evidencehttps://github.com/ojusave/beat-jev/blob/main/python/app/keeper.py#L2
Labelscall-site-verified
Olli0103/openclaw-typesafe-ai
README states: Jev returns decisions over predefined answer spaces. It does not generate conversation, prose or code. This package therefore registers a tool and no model provider, model picker entry, hook or background service.
Evidencehttps://github.com/Olli0103/openclaw-typesafe-ai/blob/main/src/client.ts#L4
Labelscall-site-verified
olsenbrands/fable-foreman
README states: Jev, from TypeSafe AI, is a decision model rather than a chatbot. It answers narrow yes/no, pick-one and score questions in under a second, for about 0.02 cents a call. Fable Foreman uses it to point the lead's attention
Evidencehttps://github.com/olsenbrands/fable-foreman/blob/main/README.md#L11
Labelsreadme-claim
OmniJev/OneJev
README states:
Evidencehttps://github.com/OmniJev/OneJev/blob/main/qev/cli.py#L143
Labelscall-site-verified
ondata/vd-jev
README states: Ask three questions about the message column, one jev-column each:
Evidencehttps://github.com/ondata/vd-jev/blob/main/README.md#L55
Labelsreadme-claim
onlyoneaman/jev-eval
README states: Jev is a model that does not write text. You give it some text and a question with fixed answers, and it gives back a probability for each answer. One call looks like this:
Evidencehttps://github.com/onlyoneaman/jev-eval/blob/main/jev_eval/backends.py#L16
Labelscall-site-verified
opencx-labs/zevals
README states: Jev is reachable through several gateways, and each names the same yes/no question differently. Three clients are bundled, all of them plain fetch with no extra dependencies:
Evidencehttps://github.com/opencx-labs/zevals/blob/main/README.md#L273
Labelsreadme-claim
openlayer-ai/jevals
README states: export AI_GATEWAY_API_KEY=... # Jev through Vercel AI Gateway. TYPESAFE_API_KEY and OPENROUTER_API_KEY also work.
Evidencehttps://github.com/openlayer-ai/jevals/blob/main/src/jevals/backends/_base.py#L65
Labelscall-site-verified
OskarLebuda/precog
README states: Asks TypeSafe Jev which link a visitor is about to click, then warms
Evidencehttps://github.com/OskarLebuda/precog/blob/main/README.md#L19
Labelsreadme-claim
oso95/x-scanner
README states: Behavioral labels on every post you scroll past on X, judged by Jev,
Evidencehttps://github.com/oso95/x-scanner/blob/main/README.md#L3
Labelsreadme-claim
PanAchy/jevvy
README states: Custom endpoints use Jevvy's default approval policy unless you replace it. Its calibration evidence applies only when the route is verified to serve the calibrated Jev model.
Evidencehttps://github.com/PanAchy/jevvy/blob/main/packages/core/src/system-one.ts#L12
Labelscall-site-verified
pavy23/web-doom
README states: Tactical policy (TypeSafe System One, Jev). At each step with an enemy
Evidencehttps://github.com/pavy23/web-doom/blob/main/README.md#L288
Labelsreadme-claim
pengchujin/ad-radar
README states: 智能识别：用你自己的 Jev API key，识别广告（硬广 / 软广 / 引流）和你选择的话题（AI、科技、军事、政治、性别对立、色情低俗、明星八卦、炒股理财、体育、游戏，也可以自己添加），标在内容旁边或折叠起来；还能估计内容由 AI 生成的比例。
Evidencehttps://github.com/pengchujin/ad-radar/blob/main/README.md#L6
Labelsreadme-claim
PerryLink/jevcore
README states: TypeSafe Jev for DeepSeek Harness
Evidencehttps://github.com/PerryLink/jevcore/blob/main/README.md#L8
Labelsreadme-claim
peterfriese/system-one-foundation-models
README states: Jev Cloud: TypeSafe AI hosted service on https://api.typesafe.ai.
Evidencehttps://github.com/peterfriese/system-one-foundation-models/blob/main/README.md#L364
Labelsreadme-claim
philippdubach/pi-jev-router
README states: pi-jev-router is a pi extension. It classifies each task with Jev (TypeSafe
Evidencehttps://github.com/philippdubach/pi-jev-router/blob/main/src/classifier.ts#L13
Labelscall-site-verified
picaye/jev-compaction
README states: Jev judges to be stale, and it shows Jev the whole conversation while deciding.
Evidencehttps://github.com/picaye/jev-compaction/blob/main/README.md#L19
Labelsreadme-claim
PistachioAIHQ/jev-synergy-screening
README states: export TYPESAFE_API_KEY="$(tr -d ' ' < ~/.config/typesafe/api_key)"
Evidencehttps://github.com/PistachioAIHQ/jev-synergy-screening/blob/main/src/config.py#L43
Labelscall-site-verified
pithings/advocaat
README states: Requests use https://ai-gateway.vercel.sh/v4/ai and model typesafe-ai/jev.
Evidencehttps://github.com/pithings/advocaat/blob/main/src/api.ts#L127
Labelscall-site-verified
PixelML/av
README states: Configure a TypeSafe System One key to make Jev refinement automatic for av ask:
Evidencehttps://github.com/PixelML/av/blob/main/README.md#L35
Labelsreadme-claim
pnthn-ai/polar_llama
README states: TypeSafe System One: A native Rust inference layer for the TypeSafe API — typed, calibrated yes/no, choice and score questions answered per row, or one Pydantic contract applied to every line of a document in a single re
Evidencehttps://github.com/pnthn-ai/polar_llama/blob/main/README.md#L22
Labelsreadme-claim
PromptEngineer48/laya-vs-jev-arena
README states: docker run -d --name arena --restart unless-stopped -p 80:8732 --cpus 1 --memory 512m -e TYPESAFE_API_KEY=your_key_here ghcr.io/promptengineer48/laya-vs-jev-arena:latest
Evidencehttps://github.com/PromptEngineer48/laya-vs-jev-arena/blob/main/server.py#L29
Labelscall-site-verified
psyb0t/aigate
README states: | decidealot _(optional, DECIDEALOT=1 and/or DECIDEALOT_CUDA=1)_ | Typed decisions with local Laya, Von, CLM, and hosted TypeSafe Jev over the TypeSafe System One API. POST /v1/systemone takes a model selector, a state,
Evidencehttps://github.com/psyb0t/aigate/blob/main/README.md#L179
Labelsreadme-claim
PyModel/jev-judge-mcp
README states: uvx --from 'jev-judge-mcp[typesafe]' jev-judge-mcp setup
Evidencehttps://github.com/PyModel/jev-judge-mcp/blob/main/evals/confinement/broker.py#L16
Labelscall-site-verified
qddegtya/qualm
README states: Jev is the model. This is what qualm adds on top of calling its HTTP API yourself.
Evidencehttps://github.com/qddegtya/qualm/blob/main/README.md#L25
Labelsreadme-claim
qkal/Canny
README states: Jev
Evidencehttps://github.com/qkal/Canny/blob/main/README.md#L155
Labelsreadme-claim
QuentinDanblon/pi-fast-jev-compaction
README states: anything. It asks Jev, over the whole conversation, whether each old tool call and each
Evidencehttps://github.com/QuentinDanblon/pi-fast-jev-compaction/blob/main/index.ts#L206
Labelscall-site-verified
Query-farm/vgi-typesafe
README states:
Evidencehttps://github.com/Query-farm/vgi-typesafe/blob/main/vgi_typesafe/mock_server.py#L39
Labelscall-site-verified
r-ms/mini-jev
README states: What a Jev-style interface looks like on a frozen model: classify against a schema that arrives with the request by reading next-token logits, not by generating JSON. Measured on Qwen3-4B.
Evidencehttps://github.com/r-ms/mini-jev/blob/main/README.md#L3
Labelsreadme-claim
RafalWilinski/vibecheck
README states: A Chrome and Firefox extension that runs your draft post through TypeSafe's Jev before you hit Post. It renders a scorecard under the composer with virality, funniness, informativeness, clarity, insult level, ragebait, c
Evidencehttps://github.com/RafalWilinski/vibecheck/blob/main/README.md#L3
Labelsreadme-claim
rajivkuriakose/typesafe-jev-examples
README states: TypeSafe's direct API is behind an early-access waitlist. OpenRouter serves the
Evidencehttps://github.com/rajivkuriakose/typesafe-jev-examples/blob/main/src/jevx/client.py#L17
Labelscall-site-verified
ranjan2829/AskJev
README states: Talk to Claude in plain English. AskJev drives Brave/Chrome. TypeSafe Jev decides on-page. Guard freezes irreversible clicks.
Evidencehttps://github.com/ranjan2829/AskJev/blob/main/mcp/src/jev-client.ts#L16
Labelscall-site-verified
RayenMlayeh/jevcrawl
README states: | TYPESAFE_API_KEY | Jev API key (required) | none |
Evidencehttps://github.com/RayenMlayeh/jevcrawl/blob/main/README.md#L202
Labelsreadme-claim
rbalch/typesafeai-review
README states: slices the diff, asks Jev (TypeSafe's System One model) narrow typed questions per hunk,
Evidencehttps://github.com/rbalch/typesafeai-review/blob/master/README.md#L4
Labelsreadme-claim
rchovatiya88/cyber-breach-jev
README states: An infinite 3D arcade cyberpunk arena shooter built with Three.js and powered by Jev—the sub-100ms "System One" decision model developed by TypeSafe AI (released September 2026).
Evidencehttps://github.com/rchovatiya88/cyber-breach-jev/blob/main/backend/bot_pilot.py#L50
Labelscall-site-verified
reachjalil/jevlogs
README states:
Evidencehttps://github.com/reachjalil/jevlogs/blob/main/README.md#L2
Labelsreadme-claim
ReallyArtificial/stuntdouble
README states: Find out whether a local decision model can replace Jev on your traffic before you switch.
Evidencehttps://github.com/ReallyArtificial/stuntdouble/blob/main/sidecars/kev-space.mjs#L42
Labelscall-site-verified
realZachi/pg-jev
README states:
Evidencehttps://github.com/realZachi/pg-jev/blob/master/README.md#L2
Labelsreadme-claim
realZachi/typesafe-adblock
README states: BYOK: bring your own key. There is no backend. You paste your own TypeSafe API key
Evidencehttps://github.com/realZachi/typesafe-adblock/blob/main/src/typesafe.js#L5
Labelscall-site-verified
receptron/laya
README states: implementation (RLAgent.system_one) and as TypeSafe Jev's system_one API, and the output
Evidencehttps://github.com/receptron/laya/blob/main/README.md#L15
Labelsreadme-claim
reinhard-z/vision-jev
README states: Move an object to ask Jev again. Drag it off the road or click its × to remove it.
Evidencehttps://github.com/reinhard-z/vision-jev/blob/main/README.md#L24
Labelsreadme-claim
RenaGao/jev-dataops
README states: Screenshots show the repository's public demo running locally with its bundled synthetic example. The measurements demonstrate the workflow, not JEV screening quality or LLM performance.
Evidencehttps://github.com/RenaGao/jev-dataops/blob/main/jev_dataops/jev.py#L23
Labelscall-site-verified
rohanarun/computer-use-cache
README states: Set your own TypeSafe API key to enable JEV in either server:
Evidencehttps://github.com/rohanarun/computer-use-cache/blob/main/server.py#L85
Labelscall-site-verified
rokbenko/quackd
README states: quackd run arm-grip-check --robot arm-01 --by-hand --decision-llm jev --decision-mode shadow
Evidencehttps://github.com/rokbenko/quackd/blob/main/quackd/agent/decision/systemone.py#L100
Labelscall-site-verified
RomanSlack/jev-drone
README states: jev-drone
Evidencehttps://github.com/RomanSlack/jev-drone/blob/main/README.md#L1
Labelsreadme-claim
romeromarcelo/jev-retrieval
README states:
Evidencehttps://github.com/romeromarcelo/jev-retrieval/blob/main/src/jev/client.rs#L28
Labelscall-site-verified
rorshopping/jev-on-a-laptop
README states: TypeSafe's own workflow evals (https://evals.typesafe.ai/) put Jev at 67.8% mean accuracy (61.7–76.0% per workflow) against a frontier consensus (average of GPT-6 Astra and Fable 5.1 answering every question), at $0.0004
Evidencehttps://github.com/rorshopping/jev-on-a-laptop/blob/main/README.md#L103
Labelsreadme-claim
runta-dev/jot
README states: ![Powered by Jev](https://typesafe.ai/)
Evidencehttps://github.com/runta-dev/jot/blob/main/README.md#L19
Labelsreadme-claim
rupeshpoojary9/poorjev
README states: The poor man's Jev. An open source, local-first "System One" decision layer for LLM apps: typed decisions with provably calibrated confidence . No API key. No waitlist.
Evidencehttps://github.com/rupeshpoojary9/poorjev/blob/main/crossbench/jev_client.py#L8
Labelscall-site-verified
ryana/jevify
README states: TypeSafe introduction
Evidencehttps://github.com/ryana/jevify/blob/main/README.md#L15
Labelsreadme-claim
safzanpirani/pi-jev-skill-picker
README states: One skill_search call costs about 38,600 Jev input tokens, or $0.0016 at $42 per billion. Jev bills input only. Against gpt-6-astra that is under 1% of what a single un-stripped request wastes.
Evidencehttps://github.com/safzanpirani/pi-jev-skill-picker/blob/master/extensions/jev.ts#L12
Labelscall-site-verified
samdotmak/jev-recall
README states: Jev Recall gives you LLM re-ranker quality retreival at semantic search prices and speed
Evidencehttps://github.com/samdotmak/jev-recall/blob/main/web/lib/systems.ts#L146
Labelscall-site-verified
samtay32/jev-system-architect
README states: A system-architecture skill for TypeSafe AI's Jev / System One. Continuously asks: *Where does this system contain fuzzy semantic judgment that should become a small Jev decision primitive?*
Evidencehttps://github.com/samtay32/jev-system-architect/blob/main/README.md#L3
Labelsreadme-claim
santos-sanz/jev-audio-beeper
README states: Private TypeScript proof of concept: identify Spanish profanity with Jev's typed probabilistic decisions and replace the matching word intervals with a beep without changing the audio duration.
Evidencehttps://github.com/santos-sanz/jev-audio-beeper/blob/main/index.ts#L1
Labelscall-site-verified
savka777/jev-use
README states:
Evidencehttps://github.com/savka777/jev-use/blob/main/Sources/JevCore/Decision.swift#L177
Labelscall-site-verified
schwarzschlyle/immune
README states: export TYPESAFE_API_KEY=... # TypeSafe Jev, which Immune asks about each call
Evidencehttps://github.com/schwarzschlyle/immune/blob/main/src/immune/sensing/jev.py#L15
Labelscall-site-verified
scienthoon/jev-ood-calibration
README states: Jev's probabilities are quantised to 0.01 and Choice/Score use the endpoints freely, so a correct answer sometimes receives exactly 0. A temperature cannot
Evidencehttps://github.com/scienthoon/jev-ood-calibration/blob/main/README.md#L39
Labelsreadme-claim
sdras/system-one-explainer
README states: TypeSafe’s System One terminology and Jev quickstart are discussed in the final case study. Choice, Score, Noul, and distribution-derived confidence are specific API details.
Evidencehttps://github.com/sdras/system-one-explainer/blob/main/README.md#L31
Labelsreadme-claim
SeeAPI/awesome-jev-use-cases
README states:
Evidencehttps://github.com/SeeAPI/awesome-jev-use-cases/blob/main/recipes/model-routing/run.py#L14
Labelscall-site-verified
sgzmd/rss-morning
README states: Jev classification on cheap RSS metadata (TypeSafe System One)
Evidencehttps://github.com/sgzmd/rss-morning/blob/main/README.md#L16
Labelsreadme-claim
shaharia-lab/jev-cli
README states:
Evidencehttps://github.com/shaharia-lab/jev-cli/blob/main/crates/jev-cli/src/help/docs.rs#L813
Labelscall-site-verified
shamazharikh/qwen-rlcd
README states: Training uses RLCD (Reinforcement Learning for Calibrated Decisions). The objective is decisions plus calibrated probabilities. TypeSafe argues that RLHF hurts calibration through sycophancy and mode dropping.
Evidencehttps://github.com/shamazharikh/qwen-rlcd/blob/main/README.md#L160
Labelsreadme-claim
shantanugoel/ask-jev-skill
README states: Hermes skill: call TypeSafe Jev (jev-latest) as a typed tiebreaker. Jev is not a chat model. It returns Choice / Score / Noul answers with probabilities so an agent can act or escalate.
Evidencehttps://github.com/shantanugoel/ask-jev-skill/blob/main/scripts/askjev.py#L15
Labelscall-site-verified
shantanugoel/mario-jev
README states: Jev receives structured RAM observations and answers focused questions about movement, starting a jump, and sustaining
Evidencehttps://github.com/shantanugoel/mario-jev/blob/main/src/mario_jev/policy.py#L3
Labelscall-site-verified
sharziki/semdecide
README states: Typed semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev.
Evidencehttps://github.com/sharziki/semdecide/blob/main/src/reflex_guard/cli.py#L180
Labelscall-site-verified
shhivv/arc-cua
README states: not use decision models, JEV or TypeSafe; it is a standalone driver.
Evidencehttps://github.com/shhivv/arc-cua/blob/master/src/arc_cua/policies/typesafe.py#L26
Labelscall-site-verified
shinshin86/aituber-onair
README states: | typesafe | TypeSafe AI | jev-latest | https://api.typesafe.ai/v1/systemone |
Evidencehttps://github.com/shinshin86/aituber-onair/blob/main/packages/comment-intelligence/README.md#L291
Labelsreadme-claim
shitianfang/jev-use
README states: hand the tasks that need no text output to Jev — faster steps, fewer
Evidencehttps://github.com/shitianfang/jev-use/blob/main/README.md#L7
Labelsreadme-claim
shivendrasoni/vector-cache
README states: The default judge is TypeSafe Jev (vendor-quoted ~100 ms per call).
Evidencehttps://github.com/shivendrasoni/vector-cache/blob/main/README.md#L98
Labelsreadme-claim
ShuhanSun/jev-oas-sentinel
README states: jev-oas-sentinel compares two OpenAPI documents in two layers:
Evidencehttps://github.com/ShuhanSun/jev-oas-sentinel/blob/main/src/jev_oas_sentinel/jev.py#L19
Labelscall-site-verified
sileod/tasksource
README states: (pick one option), score (an ordered scale) and noul (yes/no or a probability). This is the Jev / System One request format.
Evidencehttps://github.com/sileod/tasksource/blob/main/README.md#L76
Labelsreadme-claim
socai-io/jev-social
README states:
Evidencehttps://github.com/socai-io/jev-social/blob/main/src/classifier.js#L222
Labelscall-site-verified
sonnylazuardi/superterminal
README states: The ranking comes from Jev,
Evidencehttps://github.com/sonnylazuardi/superterminal/blob/main/README.md#L58
Labelsreadme-claim
sorrycc/typesafe-snake
README states: TypeSafe's Jev (a System One decision model, not an LLM) plays Snake in real time.
Evidencehttps://github.com/sorrycc/typesafe-snake/blob/master/server/index.ts#L2
Labelscall-site-verified
sosopop/jev_stock
README states: My current view is that JEV is more useful here as a disciplined reasoning layer than as a proven quantitative trading model.
Evidencehttps://github.com/sosopop/jev_stock/blob/main/jev_hk_predict.py#L29
Labelscall-site-verified
SoundBlaster/Jev4Mellea
README states: A small Python adapter that brings TypeSafe Jev's semantic checks into
Evidencehttps://github.com/SoundBlaster/Jev4Mellea/blob/main/src/mellea_jev/providers/categorical.py#L45
Labelscall-site-verified
SREGym/SREGym
README states: Jev is disabled by default. To enable it for Codex, set TYPESAFE_API_KEY and run:
Evidencehttps://github.com/SREGym/SREGym/blob/main/clients/jev/client.py#L14
Labelscall-site-verified
sriganesh/jevibe-check
README states: Usage shows request counts and estimated cost. Set token prices under Cost estimate, or use Clear stats to reset the counters. Your key and settings are kept. Check TypeSafe for actual charges.
Evidencehttps://github.com/sriganesh/jevibe-check/blob/main/extension/background.js#L133
Labelscall-site-verified
steven-shoemaker/hunch
README states: To reach Jev through a gateway your company already uses, pass gateway="openrouter" (reads OPENROUTER_API_KEY) or gateway="vercel" (reads AI_GATEWAY_API_KEY) to configure. Everything else works the same.
Evidencehttps://github.com/steven-shoemaker/hunch/blob/main/src/hunch/client.py#L37
Labelscall-site-verified
steven-shoemaker/hunch-js
README states: To reach Jev through a gateway your company already uses, pass gateway: "openrouter" (reads OPENROUTER_API_KEY) or gateway: "vercel" (reads AI_GATEWAY_API_KEY) to configure. Everything else works the same.
Evidencehttps://github.com/steven-shoemaker/hunch-js/blob/main/src/client.ts#L1
Labelscall-site-verified
STRML/omp-jevens-classifier
README states: Jev-judged permission checks for OMP's bash tool, and for eval payloads that spawn
Evidencehttps://github.com/STRML/omp-jevens-classifier/blob/main/jev.ts#L64
Labelscall-site-verified
sufianetaouil/every
README states: every needs a Jev API key. If you don't have one, join the hosted-tier waitlist:
Evidencehttps://github.com/sufianetaouil/every/blob/main/every/judge.py#L16
Labelscall-site-verified
sumleo/prompt2jev
README states: Natural language, an LLM prompt, or the code that runs one in. A Jev decision out: typed questions and a runnable script.
Evidencehttps://github.com/sumleo/prompt2jev/blob/main/skills/prompt2jev/scripts/prompt2jev.py#L27
Labelscall-site-verified
superagents-lab/jev-search
README states: Search the web in plain language. A decision model such as TypeSafe's Jev, Cloudflare's Clef or OpenAI's GPT-6 Luna chooses sources, time ranges and search terms, then ranks the results returned through Search1API. You g
Evidencehttps://github.com/superagents-lab/jev-search/blob/main/README.md#L5
Labelsreadme-claim
supercorp-ai/supercov
README states: export TYPESAFE_API_KEY=... # get one at https://typesafe.ai
Evidencehttps://github.com/supercorp-ai/supercov/blob/main/crates/supercov-cli/src/quality/tests.rs#L2768
Labelscall-site-verified
szczyglis-dev/py-gpt
README states: Jev / System One (inline) - integrates TypeSafe AI Jev for fast, typed semantic decisions over structured state, including classification, routing, selection, verification, and scoring.
Evidencehttps://github.com/szczyglis-dev/py-gpt/blob/master/src/pygpt_net/plugin/jev/worker.py#L106
Labelscall-site-verified
tacticocc/Jevbridge
README states: ACP and MCP adapter that bridges TypeSafe Jev with any LLM.
Evidencehttps://github.com/tacticocc/Jevbridge/blob/main/src/types.ts#L111
Labelscall-site-verified
tamnd/kime
README states: The base URL defaults to http://127.0.0.1:8000 in place of https://api.typesafe.ai.
Evidencehttps://github.com/tamnd/kime/blob/main/ts/README.md#L22
Labelsreadme-claim
tanghaojin/x-smart-tags
README states: 扩展通过 Background Service Worker 直接调用 https://api.typesafe.ai/v1/systemone。
Evidencehttps://github.com/tanghaojin/x-smart-tags/blob/main/README.md#L42
Labelsreadme-claim
tanxarx/awesome-jev
README states: A curated list of resources, open-source clones, integrations, and engineering playbooks for Jev — TypeSafe AI's non-generative "System 1" decision model.
Evidencehttps://github.com/tanxarx/awesome-jev/blob/main/README.md#L3
Labelsreadme-claim
TauricResearch/TradingAgents
README states: export TYPESAFE_API_KEY=... # Jev social-post screening (optional)
Evidencehttps://github.com/TauricResearch/TradingAgents/blob/main/tradingagents/agents/post_screen.py#L68
Labelscall-site-verified
tbdavid2019/ai-hedge-fund-API
README states: Fallback Tier-3: TypeSafe Official Service (https://api.typesafe.ai/v1/systemone)
Evidencehttps://github.com/tbdavid2019/ai-hedge-fund-API/blob/main/README.md#L57
Labelsreadme-claim
The-Vibe-Company/quivr
README states: That is far under Jev's budget of 32k tokens for the state plus the longest
Evidencehttps://github.com/The-Vibe-Company/quivr/blob/main/plugins/alerts/README.md#L292
Labelsreadme-claim
TholeG/typesafe-chess
README states: Two virtual chess players, both powered by TypeSafe's System One model Jev.
Evidencehttps://github.com/TholeG/typesafe-chess/blob/main/README.md#L3
Labelsreadme-claim
TianyuCodings/JevHarness
README states: | docs/ | Task authoring, a recorded Jev call, comparison video, and website screenshots |
Evidencehttps://github.com/TianyuCodings/JevHarness/blob/main/README.md#L212
Labelsreadme-claim
timpratim/macbrow
README states: LiveKit Agents for the voice loop, TypeSafe's Jev
Evidencehttps://github.com/timpratim/macbrow/blob/main/README.md#L26
Labelsreadme-claim
tinyhumansai/opencompany
README states: asked of Jev — TypeSafe's System One routing model — through the TinyHumans
Evidencehttps://github.com/tinyhumansai/opencompany/blob/main/README.md#L114
Labelsreadme-claim
TKY-27/JevSlop
README states: Eight atomic detail Score questions plus a Jev overall Score and choice in one systemOne request.
Evidencehttps://github.com/TKY-27/JevSlop/blob/main/functions/api/evaluate.ts#L1
Labelscall-site-verified
togethercomputer/tev1
README states: Jev-inspired implementation and does not use Jev's answers as training labels.
Evidencehttps://github.com/togethercomputer/tev1/blob/main/README.md#L102
Labelsreadme-claim
TokenTrim/jev-routing-experiment
README states: Jev is not a text model. It returns typed decisions (Choice / Score / Noul) with calibrated
Evidencehttps://github.com/TokenTrim/jev-routing-experiment/blob/main/jev_router/jev.py#L17
Labelscall-site-verified
tonone-ai/tonone
README states: | JEV_API_KEY or TYPESAFE_API_KEY | https://api.typesafe.ai/v1/systemone | jev-latest | jev |
Evidencehttps://github.com/tonone-ai/tonone/blob/main/lib/jev/README.md#L220
Labelsreadme-claim
tonsky/tgadmin
README states: With Jev
Evidencehttps://github.com/tonsky/tgadmin/blob/main/README.md#L8
Labelsreadme-claim
tpaulshippy/shady-town
README states: Decisions and thresholds stay in code. Built on TypeSafe's Jev via
Evidencehttps://github.com/tpaulshippy/shady-town/blob/main/README.md#L88
Labelsreadme-claim
trancong12102/agentskills
README states: | answer audit (optional) | JEV_API_KEY | Create a key at console.typesafe.ai/keys, then export JEV_API_KEY=… (TYPESAFE_API_KEY also works). Turns on Jev's two extra checks in scripts/audit-answers.py. |
Evidencehttps://github.com/trancong12102/agentskills/blob/main/README.md#L38
Labelsreadme-claim
trpc-group/trpc-agent-go
README states: For Jev, set JEV_BASE_URL=https://api.typesafe.ai, configure JEV_API_KEY
Evidencehttps://github.com/trpc-group/trpc-agent-go/blob/main/internal/systemone/README.md#L63
Labelsreadme-claim
truespar/sentio
README states: provider = "jev"
Evidencehttps://github.com/truespar/sentio/blob/main/README.md#L998
Labelsreadme-claim
turenlabs/turenos
README states: The detector uses one request with Noul questions for danger and confirmation, a Score for risk, and a Choice for category. Set TYPESAFE_ENDPOINT only if using a compatible HTTPS endpoint; plain HTTP is accepted only for
Evidencehttps://github.com/turenlabs/turenos/blob/main/command-guard/README.md#L41
Labelsreadme-claim
tyler-dot-earth/patdown
README states: The judge is swappable. The default backend uses Effect Decision / DecisionModel with TypeSafe; rules and CLI commands use a provider-neutral interface.
Evidencehttps://github.com/tyler-dot-earth/patdown/blob/main/scripts/probe-jev-input-size.mjs#L25
Labelscall-site-verified
tylergibbs1/sift
README states: Load dist/ as an unpacked extension in chrome://extensions, then enter your TypeSafe API key on
Evidencehttps://github.com/tylergibbs1/sift/blob/main/scripts/smoke.ts#L74
Labelscall-site-verified
tylerjharden/ailerix
README states: POST /api/v1/systemone — Jev-compatible Choice / Score / Noul API
Evidencehttps://github.com/tylerjharden/ailerix/blob/main/src/components/playground-client.tsx#L45
Labelscall-site-verified
typakon4/jev-layer
README states:
Evidencehttps://github.com/typakon4/jev-layer/blob/main/src/providers/demo.mjs#L36
Labelscall-site-verified
TypeLLM/TypeLLM
README states: TypeLLM brings type-safe generation to existing autoregressive LLMs without changing their architecture or weights. Inspired by TypeSafe AI's Jev, it lets models retain their native thinking and free-form generation whil
Evidencehttps://github.com/TypeLLM/TypeLLM/blob/main/README.md#L48
Labelsreadme-claim
TypeSafeAI/typesafe-playground
README states: Small experiments. Clear decisions. This is an independent community project, not an official TypeSafe AI product, production agent harness, or claim that a typed answer is correct.
Evidencehttps://github.com/TypeSafeAI/typesafe-playground/blob/main/lib/serverJev.ts#L52
Labelscall-site-verified
UditAkhourii/quicksilver
README states: Jev, TypeSafe's System One model. Jev returns typed
Evidencehttps://github.com/UditAkhourii/quicksilver/blob/main/README.md#L21
Labelsreadme-claim
uehaj/sys1grep
README states: sys1grep: endpoint api.typesafe.ai/v1/systemone (default), model jev-latest (default)
Evidencehttps://github.com/uehaj/sys1grep/blob/main/README.md#L229
Labelsreadme-claim
uezo/aiavatarkit
README states: Gates — Smart Turn, Namo Turn, Jev, OpenAI Decisions, LLM turn gate, filler-only, session hold, custom gates
Evidencehttps://github.com/uezo/aiavatarkit/blob/main/aiavatar/sts/vad/turn_end_gates/jev.py#L172
Labelscall-site-verified
unownone/jevsume
README states: ATS-friendly resume review powered by Jev (TypeSafe System One). The frontend extracts resume text the way a parser would, then a Cloudflare Worker runs typed JEV questions and composes a JevScore.
Evidencehttps://github.com/unownone/jevsume/blob/main/readme.md#L3
Labelsreadme-claim
uu889/laya-opencv
README states: | TypeSafe 官方 | https://api.typesafe.ai | TypeSafe 控制台的密钥 |
Evidencehttps://github.com/uu889/laya-opencv/blob/main/README.md#L386
Labelsreadme-claim
v-modal/awesome-jev-tools
README states: A curated list of public projects and developer patterns built on Jev, TypeSafe AI's System One model for typed decisions.
Evidencehttps://github.com/v-modal/awesome-jev-tools/blob/main/README.md#L7
Labelsreadme-claim
valentynkit/awesome-jev-typesafe
README states:
Evidencehttps://github.com/valentynkit/awesome-jev-typesafe/blob/main/scripts/jev-client.mjs#L5
Labelscall-site-verified
valentynkit/jev-commit
README states: that the two agree. This does, in one call to Jev, before the commit lands.
Evidencehttps://github.com/valentynkit/jev-commit/blob/main/jev_commit/jev.py#L18
Labelscall-site-verified
valentynkit/jev-skip
README states: Gateway shim rather than the direct API. Re-measure on api.typesafe.ai before pinning
Evidencehttps://github.com/valentynkit/jev-skip/blob/main/README.md#L19
Labelsreadme-claim
vinilana/live-jev
README states: TypeSafe's Jev (a "System One" decision model)
Evidencehttps://github.com/vinilana/live-jev/blob/main/README.md#L4
Labelsreadme-claim
vnmoorthy/siege
README states: Built at CoreWeave Hacks: Agent Loops (Weights & Biases, AGI House, TypeSafe AI), San Francisco, September 13 to 14, 2026.
Evidencehttps://github.com/vnmoorthy/siege/blob/main/README.md#L248
Labelsreadme-claim
w3cj/jev-chat
README states: Jev does not produce text. Every text argument, such as a search query, a task title or a city, is
Evidencehttps://github.com/w3cj/jev-chat/blob/main/apps/server/src/jev/client.ts#L1
Labelscall-site-verified
walidboulanouar/awesome-jev-use-cases
README states:
Evidencehttps://github.com/walidboulanouar/awesome-jev-use-cases/blob/main/README.md#L2
Labelsreadme-claim
waynesutton/ask-jev-ai
README states: | Judge | Jev, TypeSafe System One, through the Convex AI Gateway Decisions endpoint (typesafe/jev-1.13) on a deployment token. No key. TypeSafe direct is the fallback when a key is set. | Decisions, docs.typesafe.ai |
Evidencehttps://github.com/waynesutton/ask-jev-ai/blob/main/README.md#L40
Labelsreadme-claim
WeSecureYou/Jev-test
README states: The project works immediately without credentials. When JEV_API_KEY is absent, it logs a warning and uses deterministic, occupation-aware mock data with the same validated shape as a live Jev response.
Evidencehttps://github.com/WeSecureYou/Jev-test/blob/main/src/services/jevClient.ts#L9
Labelscall-site-verified
wfzyx/von
README states: von serve exposes /v1/systemone, byte-compatible with the TypeSafe specification. Anything that talks to Jev talks to Von by changing the base URL; the SDKs do the same via VON_BASE_URL.
Evidencehttps://github.com/wfzyx/von/blob/master/js/src/client.ts#L10
Labelscall-site-verified
whyashthakker/awesome-jev-use-cases
README states: git clone https://github.com/whyashthakker/awesome-jev-use-cases.git
Evidencehttps://github.com/whyashthakker/awesome-jev-use-cases/blob/main/shared/providers.js#L16
Labelscall-site-verified
Wizhill05/typesafe-image-diffusion
README states: Jev (via TypeSafe System One) is a judgment model. You give it state, ask multiple choice questions, and it picks answers with confidence scores. It classifies things. It does not draw things.
Evidencehttps://github.com/Wizhill05/typesafe-image-diffusion/blob/main/fix_synthesizer.py#L3
Labelscall-site-verified
wobsoriano/is-jeven
README states: Uses TypeSafe AI's Jev model under the hood to determine if a number is even.
Evidencehttps://github.com/wobsoriano/is-jeven/blob/main/index.js#L19
Labelscall-site-verified
wustep/jev-playground
README states: npm test # vitest: renderer invariants, Jev request shapes, proxy, MIDI round-trip, inbox/match stubs
Evidencehttps://github.com/wustep/jev-playground/blob/main/server/jevHandler.ts#L20
Labelscall-site-verified
Xiaooolong/vev
README states: the official Jev API (shape reference, costs a few cents)
Evidencehttps://github.com/Xiaooolong/vev/blob/main/conformance/README.md#L17
Labelsreadme-claim
xinyao27/jevonian
README states: Jev picks the route for jevonian/auto — model and thinking depth in a single call.
Evidencehttps://github.com/xinyao27/jevonian/blob/main/internal/brain/types.go#L45
Labelscall-site-verified
xiwan/acp-bridge
README states: | Auto agent routing | Send a task to the virtual agent auto and let Jev (TypeSafe System One) pick the best-fit agent with a calibrated confidence score; falls back safely |
Evidencehttps://github.com/xiwan/acp-bridge/blob/main/README.md#L48
Labelsreadme-claim
y0usaf/pi-jev
README states: The gate sends the working directory, the tool name, the last user message (first 1200 characters), and the tool's arguments to api.typesafe.ai. For write and edit those arguments contain file content. The output judge s
Evidencehttps://github.com/y0usaf/pi-jev/blob/main/README.md#L145
Labelsreadme-claim
yairshy/decido
README states: ordinary Python. Start with Jev or supply your own decision provider.
Evidencehttps://github.com/yairshy/decido/blob/main/src/decido/providers/typesafe.py#L111
Labelscall-site-verified
yan-labs/yan-skills
README states: | jev | Typesafe(JEV / System One) | https://api.typesafe.ai/v1/systemone,Authorization: Bearer 鉴权(protocol: "typesafe-systemone",不是 Anthropic Messages/OpenAI 协议) | ⚠️ 不支持 run/run-many——它是结构化决策 API,不生成文本、不支持多轮工具调用,只能用下面「
Evidencehttps://github.com/yan-labs/yan-skills/blob/main/agent-fleet/README.md#L123
Labelsreadme-claim
Yifan-Lan/awesome-jev-robustness
README states: entries · jev-1.13.0 in 111, jev-1.14.0 in 1, other decision models (Laya, Kev, Clef, Decision-1, OpenAI Decisions, open Jev-style checkpoints) in 31 · snapshot 2026-10-25 · numbers are the authors' own
Evidencehttps://github.com/Yifan-Lan/awesome-jev-robustness/blob/main/README.md#L5
Labelsreadme-claim
Yinsongxu/LLM2Jev
README states: Turn your LLM / MLLM into a Jev-style decision model. Zero training required.
Evidencehttps://github.com/Yinsongxu/LLM2Jev/blob/main/demos/web/server.py#L19
Labelscall-site-verified
ZeroGold/call-coach-ai
README states: You need a TypeSafe API key. There are three ways to run Call Coach:
Evidencehttps://github.com/ZeroGold/call-coach-ai/blob/main/lib/coach.mjs#L13
Labelscall-site-verified
ZeroTang05/VideoAdGuard
README states: | TypeSafe | https://api.typesafe.ai/v1 | jev-latest | 官方接口 |
Evidencehttps://github.com/ZeroTang05/VideoAdGuard/blob/main/README.md#L138
Labelsreadme-claim
zhengxuyu/litjev
README states: A reproduction of Jev: turn any Qwen model into a fast decision model.
Evidencehttps://github.com/zhengxuyu/litjev/blob/main/scripts/dump_prompt.py#L10
Labelscall-site-verified
zhuyansen/jev-search-rerank-eval
README states: Does a TypeSafe Jev rerank beat embedding search? Measured, with the judge-bias removed.
Evidencehttps://github.com/zhuyansen/jev-search-rerank-eval/blob/main/README.md#L3
Labelsreadme-claim
zsavage8/padflow-jev-evals
README states: them. It exists so a decision model (TypeSafe Jev, or anything else) can be
Evidencehttps://github.com/zsavage8/padflow-jev-evals/blob/main/scripts/run_baseline.py#L7
Labelscall-site-verified

Keep going on this site

Try, docs, cases, and pricing link to each other. The next page is on this site.