JevCode /Voltar à cobertura / Outras listas

Outras listas

425 entradas nesta categoria. Cada uma declara a decisão concreta e aponta evidência abrível.

• 0x7067/claude-jev

  README states: The run sends your past prompts to api.typesafe.ai. Start with --sample 250

  Evidênciahttps://github.com/0x7067/claude-jev/blob/main/eval/README.md#L130

  Rótulosreadme-claim

• 0xArx/jevegis

  README states: retrieved documents) and Trust & Safety moderation, both powered by TypeSafe's Jev

  Evidênciahttps://github.com/0xArx/jevegis/blob/main/src/lib/engine.ts#L1

  Rótuloscall-site-verified

• 0xBakeer/arbiter

  README states: Serve typed-decision models — Laya or your own — on your GPU or your Mac, with a Jev-compatible

  Evidênciahttps://github.com/0xBakeer/arbiter/blob/main/integrations/claude-code/hooks/eval.py#L57

  Rótuloscall-site-verified

• 0xNatoshi/jev-codex-router

  README states: Jev chooses a model and thinking effort together for each model call, including

  Evidênciahttps://github.com/0xNatoshi/jev-codex-router/blob/main/poc/backtest_savings.py#L157

  Rótuloscall-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.

  Evidênciahttps://github.com/0xtrou/rubikjev/blob/main/src/app/api/solve/route.ts#L127

  Rótuloscall-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.

  Evidênciahttps://github.com/2FastLabs/agent-squad/blob/main/README.md#L157

  Rótulosreadme-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.

  Evidênciahttps://github.com/3clyp50/a0-typesafe-ai/blob/main/extensions/webui/get_tool_message_handler/typesafe.js#L2

  Rótuloscall-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

  Evidênciahttps://github.com/6Mikao9/jev-agent-design-with-topk-logits-choices/blob/main/jev_agent/jev_client.py#L57

  Rótuloscall-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.

  Evidênciahttps://github.com/Aayan-DEV/aayans-yc-indexor/blob/main/README.md#L30

  Rótulosreadme-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.

  Evidênciahttps://github.com/AbdelStark/bicameral/blob/main/packages/s1-runtime/src/backends/typesafe.ts#L1

  Rótuloscall-site-verified

• abe75ch/tiltmeter

  README states: Notices your Jev decisions tilting before anything visibly breaks.

  Evidênciahttps://github.com/abe75ch/tiltmeter/blob/main/tiltmeter.py#L270

  Rótuloscall-site-verified

• AboveColin/HA-Jev

  README states: back. Jev is a decision model, not a chat model. It answers a typed question with a

  Evidênciahttps://github.com/AboveColin/HA-Jev/blob/main/README.md#L12

  Rótulosreadme-claim

• ad-si/cai

  README states: [TypeSafe]: https://docs.typesafe.ai/models

  Evidênciahttps://github.com/ad-si/cai/blob/main/readme.md#L50

  Rótulosreadme-claim

• adarshmishra07/jcm-router

  README states: level per message, using TypeSafe's Jev classifier. Trivial questions go to Haiku, everyday work to

  Evidênciahttps://github.com/adarshmishra07/jcm-router/blob/main/scripts/eval.ts#L12

  Rótuloscall-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.

  Evidênciahttps://github.com/adhyaay-karnwal/jev-chat/blob/main/src/jevchat/client.py#L7

  Rótuloscall-site-verified

• affirmitv/ghosthands

  README states: Configuration: GH_PLANNER=jev, GH_JEV_MODEL (default typesafe/jev-1.13; ~typesafe/jev-latest

  Evidênciahttps://github.com/affirmitv/ghosthands/blob/main/README.md#L221

  Rótulosreadme-claim

• afshinm/laya-mps

  README states: Run Jev-style typed decisions locally on your Mac with low RAM usage and fast responses.

  Evidênciahttps://github.com/afshinm/laya-mps/blob/main/README.md#L3

  Rótulosreadme-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。

  Evidênciahttps://github.com/Ai-trainee/awesome-jev/blob/main/README.md#L390

  Rótulosreadme-claim

• ai4curation/jevotron

  README states: in tabular, structured, and text files, SQLite, and DuckDB, powered by Jev.

  Evidênciahttps://github.com/ai4curation/jevotron/blob/main/README.md#L8

  Rótulosreadme-claim

• AiPersonacademy/jev-resume-disqualifier

  README states: Automated Candidate Knockout Engine for High-Volume Recruiting — Powered by TypeSafe Jev System One Decision Intelligence.

  Evidênciahttps://github.com/AiPersonacademy/jev-resume-disqualifier/blob/main/engine/decision_gateway.py#L20

  Rótuloscall-site-verified

• alexj11324/open-jev-approvals

  README states: When the agent is about to run a tool, a hook intercepts the call, TypeSafe

  Evidênciahttps://github.com/alexj11324/open-jev-approvals/blob/main/internal/jev/client.go#L22

  Rótuloscall-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,

  Evidênciahttps://github.com/allebee/pytest-jev/blob/main/bench/llm_judge.py#L14

  Rótuloscall-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.

  Evidênciahttps://github.com/allenporter/home-assistant-typesafe/blob/main/README.md#L34

  Rótulosreadme-claim

• alterhq/typesafe-sdk-swift

  README states: authenticated backend. Keep the TypeSafe API key in server-side secret storage. Direct API-key

  Evidênciahttps://github.com/alterhq/typesafe-sdk-swift/blob/main/Sources/TypeSafe/Requests.swift#L4

  Rótuloscall-site-verified

• altryne/jevify

  README states: Use Jev during everyday agent work, and find what it can improve in your product.

  Evidênciahttps://github.com/altryne/jevify/blob/main/scripts/jev_client.py#L32

  Rótuloscall-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.

  Evidênciahttps://github.com/andrelandgraf/safer-with-jev/blob/main/src/index.ts#L5

  Rótuloscall-site-verified

• andududu/jeview

  README states: your code → Jeview (127.0.0.1:4777) → TypeSafe (api.typesafe.ai)

  Evidênciahttps://github.com/andududu/jeview/blob/main/README.md#L9

  Rótulosreadme-claim

• Anil-matcha/awesome-jev-by-typesafe

  README states: ▶ Watch: Jev: 8 Wild Things People Already Built With TypeSafe's New AI Model

  Evidênciahttps://github.com/Anil-matcha/awesome-jev-by-typesafe/blob/main/README.md#L14

  Rótulosreadme-claim

• aniruddh-krovvidi/switchboard

  README states: A guardrail and model router for LLM gateways, built on Jev, TypeSafe AI's

  Evidênciahttps://github.com/aniruddh-krovvidi/switchboard/blob/main/jev.py#L3

  Rótuloscall-site-verified

• anishfn/shapeshift

  README states:

  Evidênciahttps://github.com/anishfn/shapeshift/blob/main/src/lib/jev/client.ts#L2

  Rótuloscall-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.

  Evidênciahttps://github.com/AnotiaWang/awesome-jev/blob/main/README.md#L178

  Rótulosreadme-claim

• AntonioCoppe/jev-harness

  README states: It is not affiliated with TypeSafe. You need a TypeSafe API key to call Jev.

  Evidênciahttps://github.com/AntonioCoppe/jev-harness/blob/main/recipes/agent-comm-harness/message-route.ts#L1

  Rótuloscall-site-verified

• AppitStudio/awesome-jev

  README states: Discover Jev-powered apps, developer resources, and runnable decision examples.

  Evidênciahttps://github.com/AppitStudio/awesome-jev/blob/main/README.md#L3

  Rótulosreadme-claim

• AppSprout-dev/Unsga3

  README states: TypeSafe / Jev Pareto scoring (optional)

  Evidênciahttps://github.com/AppSprout-dev/Unsga3/blob/main/README.md#L104

  Rótulosreadme-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,

  Evidênciahttps://github.com/ARCJ137442/jev-life/blob/main/src/client/api.ts#L222

  Rótuloscall-site-verified

• arczhi/jet

  README states: Judgment-first routing — Jev (TypeSafe System One) handles context

  Evidênciahttps://github.com/arczhi/jet/blob/main/README.md#L43

  Rótulosreadme-claim

• atharvamhaske/typesafe-sdk-go

  README states: | WithBaseURL | TYPESAFE_BASE_URL | API base URL, defaults to https://api.typesafe.ai |

  Evidênciahttps://github.com/atharvamhaske/typesafe-sdk-go/blob/main/README.md#L115

  Rótulosreadme-claim

• audreyt/paseo-spacedock

  README states: Gate judgment (Jev / TypeSafe-compatible)

  Evidênciahttps://github.com/audreyt/paseo-spacedock/blob/main/README.md#L56

  Rótulosreadme-claim

• automateyournetwork/netclaw

  README states: | JEV_BASE_URL | https://api.typesafe.ai; /v1/systemone appended when no path supplied; full custom paths accepted |

  Evidênciahttps://github.com/automateyournetwork/netclaw/blob/main/mcp-servers/jev-mcp/README.md#L42

  Rótulosreadme-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:

  Evidênciahttps://github.com/Avinash-jetwani/jevmem/blob/main/plugin/README.md#L46

  Rótulosreadme-claim

• awlevin/typesafe-computer-use

  README states:

  Evidênciahttps://github.com/awlevin/typesafe-computer-use/blob/main/typesafe_computer_use/actions.py#L9

  Rótuloscall-site-verified

• awslabs/agentcore-samples

  README states: Jev Evaluators (--with-jev)

  Evidênciahttps://github.com/awslabs/agentcore-samples/blob/main/01-features/06-observe-evaluate-optimize-your-agent/02-evaluate/custom-code-based-evaluation/README.md#L600

  Rótulosreadme-claim

• Ayush0054/metis

  README states: metis-workflow is a small Python framework for workflows powered by TypeSafe AI's

  Evidênciahttps://github.com/Ayush0054/metis/blob/main/legacy/metis-triage/src/metis_triage/_triage.py#L154

  Rótuloscall-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:

  Evidênciahttps://github.com/Baba88611/detroit-ai-player/blob/main/README.md#L189

  Rótulosreadme-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.*

  Evidênciahttps://github.com/bcharleson/jev-gtm-cookbook/blob/main/README.md#L5

  Rótulosreadme-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.

  Evidênciahttps://github.com/beamnxw/minelog/blob/main/README.md#L33

  Rótulosreadme-claim

• BeatAPI/awesome-jev

  README states:

  Evidênciahttps://github.com/BeatAPI/awesome-jev/blob/main/scripts/curate-star50-expansion-2026-09-23.mjs#L217

  Rótuloscall-site-verified

• BenCaunt/jev-box-tracking

  README states: jev-box-tracking

  Evidênciahttps://github.com/BenCaunt/jev-box-tracking/blob/main/README.md#L1

  Rótulosreadme-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

  Evidênciahttps://github.com/bestagentkits/jev-skillful/blob/main/packages/cli/src/core/eval/replay.ts#L22

  Rótuloscall-site-verified

• Bewinxed/jevgpt

  README states: TypeSafe AI's jev-latest is a decision model: it does not generate text,

  Evidênciahttps://github.com/Bewinxed/jevgpt/blob/master/src/jevgpt/sampler.py#L29

  Rótuloscall-site-verified

• bhaiG-de/jev-design-test

  README states: Prerequisites: Node 20+, and a Jev (TypeSafe) API key.

  Evidênciahttps://github.com/bhaiG-de/jev-design-test/blob/master/vite.config.ts#L5

  Rótuloscall-site-verified

• BillionsBobby/JevRouter

  README states:

  Evidênciahttps://github.com/BillionsBobby/JevRouter/blob/main/src/provider.ts#L103

  Rótuloscall-site-verified

• bladedevoff/stuntd

  README states: With the paid Jev API in front, the same demo runs with it as the teacher instead: put

  Evidênciahttps://github.com/bladedevoff/stuntd/blob/main/examples/banking/README.md#L42

  Rótulosreadme-claim

• bodepudimuneendra-netizen/laya-jev-GraphRAG

  README states: │ LAYER 2 — DECISION (Laya / Jev) ← The CPU │

  Evidênciahttps://github.com/bodepudimuneendra-netizen/laya-jev-GraphRAG/blob/main/graphrag_neo4j_laya/graphrag/models/jev.py#L7

  Rótuloscall-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.

  Evidênciahttps://github.com/bohutang/sift/blob/main/background.js#L4

  Rótuloscall-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).

  Evidênciahttps://github.com/brainstormity/Jev-X-Sentiment-Analysis/blob/main/app/services/typesafe_service.py#L3

  Rótuloscall-site-verified

• brandonbryant12/transcript-scorecard

  README states: Server-side OpenAI Decisions and TypeSafe JEV adapters for incremental transcript scoring

  Evidênciahttps://github.com/brandonbryant12/transcript-scorecard/blob/main/apps/api/src/classifier.ts#L1

  Rótuloscall-site-verified

• brnyxx/jev-ra

  README states:

  Evidênciahttps://github.com/brnyxx/jev-ra/blob/main/jev_ra/config.py#L11

  Rótuloscall-site-verified

• buberlo/jev-trader

  README states: jev-trader

  Evidênciahttps://github.com/buberlo/jev-trader/blob/main/README.md#L1

  Rótulosreadme-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。

  Evidênciahttps://github.com/bugkiwi/elons-job/blob/main/README.md#L46

  Rótulosreadme-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.

  Evidênciahttps://github.com/BunsDev/typesafe-ai-playground/blob/main/lib/serverJev.ts#L52

  Rótuloscall-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.

  Evidênciahttps://github.com/BunsDev/typesafe-ui/blob/main/README.md#L3

  Rótulosreadme-claim

• burnigtm/jev-mcp

  README states: codex mcp add jev --env TYPESAFE_API_KEY=ts_... -- node /absolute/path/to/jev-mcp/dist/index.js

  Evidênciahttps://github.com/burnigtm/jev-mcp/blob/main/src/errors.ts#L1

  Rótuloscall-site-verified

• BYK/jev-mcp

  README states: Most Jev integrations expose "ask the model a question". The hard part in practice is not asking —

  Evidênciahttps://github.com/BYK/jev-mcp/blob/main/src/tools/ask.ts#L37

  Rótuloscall-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

  Evidênciahttps://github.com/bytelabs-oss/clash-jev/blob/main/clash_jev/policy.py#L183

  Rótuloscall-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

  Evidênciahttps://github.com/caiovicentino/eikos-arena/blob/main/arena/arena.py#L31

  Rótuloscall-site-verified

• can1357/jegrep

  README states: src/jev.rs 0.97 · 458 lines shown

  Evidênciahttps://github.com/can1357/jegrep/blob/main/README.md#L122

  Rótulosreadme-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)

  Evidênciahttps://github.com/CaptainCore/captaincore/blob/master/typesafe/client.go#L188

  Rótuloscall-site-verified

• carldaws/hunch

  README states: Point Hunch at a System One endpoint. Jev is available through

  Evidênciahttps://github.com/carldaws/hunch/blob/main/README.md#L27

  Rótulosreadme-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

  Evidênciahttps://github.com/carlosedm10/agi-jev-containment/blob/main/README.md#L70

  Rótulosreadme-claim

• cbruyndoncx/AskJev-MCP

  README states: Ask everything you want to know about a state in one call rather than several — TypeSafe bills per

  Evidênciahttps://github.com/cbruyndoncx/AskJev-MCP/blob/main/src/index.ts#L6

  Rótuloscall-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

  Evidênciahttps://github.com/cequence-io/openai-scala-client/blob/master/typesafe-client/src/main/scala/io/cequence/openaiscala/typesafe/JsonFormats.scala#L125

  Rótuloscall-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.

  Evidênciahttps://github.com/Chandler-Sun/chat2jev/blob/main/src/components/answers.tsx#L49

  Rótuloscall-site-verified

• CharlesFeng0314/JEV_sees

  README states: JEV is fast, structured, and built to make decisions.

  Evidênciahttps://github.com/CharlesFeng0314/JEV_sees/blob/main/jev_sees/__init__.py#L3

  Rótuloscall-site-verified

• Charlyhno-eng/jev-document-classification

  README states: To use JEV, you need a Vercel account and an AI Gateway API key.

  Evidênciahttps://github.com/Charlyhno-eng/jev-document-classification/blob/main/README.md#L25

  Rótulosreadme-claim

• cheeaun/jevmoji

  README states: Type up to 40 characters. Get related emojis scored by TypeSafe’s Jev — many matches, not just one.

  Evidênciahttps://github.com/cheeaun/jevmoji/blob/main/README.md#L10

  Rótulosreadme-claim

• CheshiAI/Cheshi

  README states: Previous conversation recall is off by default, including for existing TypeSafe

  Evidênciahttps://github.com/CheshiAI/Cheshi/blob/main/README.md#L86

  Rótulosreadme-claim

• chez-shanpu/typesafeai-go

  README states: // A TypeSafe AI compatible server running locally without authentication.

  Evidênciahttps://github.com/chez-shanpu/typesafeai-go/blob/main/option.go#L9

  Rótuloscall-site-verified

• christos-antono/NPCTalk

  README states: | Actions and spoken orders | TypeSafe | TYPESAFE_API_KEY |

  Evidênciahttps://github.com/christos-antono/NPCTalk/blob/main/README.md#L57

  Rótulosreadme-claim

• chy4pro/jev-for-chrome

  README states: | OpenRouter | https://openrouter.ai/api/alpha/decisions | typesafe/jev-1.13 |

  Evidênciahttps://github.com/chy4pro/jev-for-chrome/blob/main/README.md#L112

  Rótulosreadme-claim

• cobanov/awesome-jev

  README states: New: Ollaya runs open decision models locally behind a Jev-compatible API.

  Evidênciahttps://github.com/cobanov/awesome-jev/blob/main/README.md#L8

  Rótulosreadme-claim

• cobusgreyling/Jev

  README states: Jev Showcase — TypeSafe System One, not chat

  Evidênciahttps://github.com/cobusgreyling/Jev/blob/main/README.md#L1

  Rótulosreadme-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).

  Evidênciahttps://github.com/cocktailpeanut/jevthoven/blob/main/app/scripts/live-smoke.mjs#L15

  Rótuloscall-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.

  Evidênciahttps://github.com/codaaiteam/jev-mcp/blob/main/README.md#L30

  Rótulosreadme-claim

• Cognipeer/agent-sdk

  README states: Against the real Jev API

  Evidênciahttps://github.com/Cognipeer/agent-sdk/blob/main/examples/jev-guardrail/README.md#L24

  Rótulosreadme-claim

• colliber/duckdb-jev

  README states: the extension talking to api.typesafe.ai.

  Evidênciahttps://github.com/colliber/duckdb-jev/blob/main/docs/README.md#L4

  Rótulosreadme-claim

• columnar-tech/jevaro

  README states: A Python batching proxy for Jev that returns

  Evidênciahttps://github.com/columnar-tech/jevaro/blob/main/README.md#L3

  Rótulosreadme-claim

• compozy/yoshi

  README states: Jev judges new context once, above a configurable size gate. Yoshi applies the

  Evidênciahttps://github.com/compozy/yoshi/blob/main/README.md#L7

  Rótulosreadme-claim

• Contrastive-LM/CLM

  README states: It performs on par with Jev across computer-use, gaming and tool-calling

  Evidênciahttps://github.com/Contrastive-LM/CLM/blob/main/src/clm/__init__.py#L6

  Rótuloscall-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:

  Evidênciahttps://github.com/CorieW/JevTest/blob/main/src/jev.ts#L122

  Rótuloscall-site-verified

• CTNicholas/jev-workflow-builder

  README states: Create an account on typesafe.ai

  Evidênciahttps://github.com/CTNicholas/jev-workflow-builder/blob/main/README.md#L14

  Rótulosreadme-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

  Evidênciahttps://github.com/danielgshea/jev-as-a-judge/blob/main/README.md#L5

  Rótulosreadme-claim

• DanRWilloughby/snifftest

  README states: judgment rules too, put a TypeSafe key in TYPESAFE_API_KEY and drop

  Evidênciahttps://github.com/DanRWilloughby/snifftest/blob/main/src/jev.ts#L50

  Rótuloscall-site-verified

• danvega/jev-spring-boot-starter

  README states: | jev.api-key | TYPESAFE_API_KEY fallback | TypeSafe API key |

  Evidênciahttps://github.com/danvega/jev-spring-boot-starter/blob/main/README.md#L145

  Rótulosreadme-claim

• Das-rebel/a3m-router

  README states: model="jev-auto" — ML decision head, calibrated probabilities, ~2ms warm

  Evidênciahttps://github.com/Das-rebel/a3m-router/blob/main/README.md#L120

  Rótulosreadme-claim

• daseinlabs/open-jev

  README states: make systemone # TypeSafe-style request against /v1/systemone

  Evidênciahttps://github.com/daseinlabs/open-jev/blob/main/demo/doom/client.py#L66

  Rótuloscall-site-verified

• davila7/jev-explained

  README states: Learn how TypeSafe's Jev makes typed, probabilistic decisions — by running it.

  Evidênciahttps://github.com/davila7/jev-explained/blob/main/src/lib/providers.ts#L21

  Rótuloscall-site-verified

• DECRUX9812/typesafe-skill-router

  README states: A TypeSafe API key (TYPESAFE_API_KEY) — create one at

  Evidênciahttps://github.com/DECRUX9812/typesafe-skill-router/blob/main/__init__.py#L30

  Rótuloscall-site-verified

• delexw/claude-code-trace

  README states: Jev and provider API keys live in the OS credential store (macOS Keychain, Windows Credential

  Evidênciahttps://github.com/delexw/claude-code-trace/blob/main/src-tauri/src/efficiency/jev.rs#L12

  Rótuloscall-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) |

  Evidênciahttps://github.com/dengyie/ai-register-machine/blob/main/README.md#L36

  Rótulosreadme-claim

• devagrawal09/jev-review

  README states: The reviewer keeps orchestration in code and uses Jev for bounded judgments:

  Evidênciahttps://github.com/devagrawal09/jev-review/blob/main/src/review/codebase-judgments.ts#L3

  Rótuloscall-site-verified

• devagrawal09/stanley-code

  README states: For built-ins, Jev answers fixed-choice questions about each piece. Using your required TypeSafe API key,

  Evidênciahttps://github.com/devagrawal09/stanley-code/blob/main/README.md#L94

  Rótulosreadme-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。

  Evidênciahttps://github.com/Devin-AXIS/jev-dsh-decision/blob/main/README.md#L137

  Rótulosreadme-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.

  Evidênciahttps://github.com/DevMortimer/pi-warden/blob/main/scripts/slop-cases.mjs#L77

  Rótuloscall-site-verified

• devtooligan/jevscan-evm

  README states: Produce a heat map of likely bugs - in seconds, for pennies - built with TypeSafe's Jev.

  Evidênciahttps://github.com/devtooligan/jevscan-evm/blob/main/README.md#L10

  Rótulosreadme-claim

• dfinke/Jev

  README states:

  Evidênciahttps://github.com/dfinke/Jev/blob/main/README.md#L2

  Rótulosreadme-claim

• Dicklesworthstone/skillranker

  README states: The right skill for the next step, powered by Jev-compatible providers.

  Evidênciahttps://github.com/Dicklesworthstone/skillranker/blob/main/src/jev/client/tests.rs#L100

  Rótuloscall-site-verified

• Dimweaker/jev-libero

  README states:

  Evidênciahttps://github.com/Dimweaker/jev-libero/blob/main/src/jev_libero/client.py#L14

  Rótuloscall-site-verified

• docxology/daf-jev

  README states: Modular, composable Python client and decision toolkit for the TypeSafe Jev

  Evidênciahttps://github.com/docxology/daf-jev/blob/main/src/daf_jev/__init__.py#L23

  Rótuloscall-site-verified

• doeixd/discern

  README states: error. Provider-neutral: runs on TypeSafe's Jev, or any other DecisionModel.

  Evidênciahttps://github.com/doeixd/discern/blob/main/README.md#L7

  Rótulosreadme-claim

• dominicrico/jev-router

  README states: | jev (default) | https://api.typesafe.ai/v1/systemone | jev-latest | TYPESAFE_API_KEY or /jev key (required) |

  Evidênciahttps://github.com/dominicrico/jev-router/blob/main/README.md#L94

  Rótulosreadme-claim

• donvito/ai-backends

  README states: | TypeSafe Jev | System One decision model: choice, score, and noul questions | Available |

  Evidênciahttps://github.com/donvito/ai-backends/blob/main/README.md#L99

  Rótulosreadme-claim

• dorkitude/webctl

  README states: Smart web search CLI for agents, backed by Jev. Saves a lot of tokens.

  Evidênciahttps://github.com/dorkitude/webctl/blob/main/README.md#L3

  Rótulosreadme-claim

• Dujaydis/JevSysUno

  README states: A reference integration for TypeSafe AI's Jev, the first "System One" model: typed

  Evidênciahttps://github.com/Dujaydis/JevSysUno/blob/master/README.md#L3

  Rótulosreadme-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.

  Evidênciahttps://github.com/ellistev/typesafe-minecraft-demo/blob/main/src/decisions.cjs#L45

  Rótuloscall-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) |

  Evidênciahttps://github.com/equationalapplications/system-one-reviewer/blob/main/README.md#L236

  Rótulosreadme-claim

• eriestra/browser-use-olympics

  README states: echo 'TYPESAFE_API_KEY=...' > ~/.config/typesafe/env # chmod 600

  Evidênciahttps://github.com/eriestra/browser-use-olympics/blob/main/almond-fastloop.mjs#L102

  Rótuloscall-site-verified

• Eriskii/ErisLint

  README states: anything useful, then map Jev's answers to warnings or errors.

  Evidênciahttps://github.com/Eriskii/ErisLint/blob/main/src/jev.rs#L24

  Rótuloscall-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

  Evidênciahttps://github.com/EthanAlgoX/AIStock/blob/main/README.md#L148

  Rótulosreadme-claim

• etweisberg/jev-ui

  README states:

  Evidênciahttps://github.com/etweisberg/jev-ui/blob/main/apps/demo/scripts/check-key.mjs#L5

  Rótuloscall-site-verified

• EugeneBoondock/jevsql

  README states:

  Evidênciahttps://github.com/EugeneBoondock/jevsql/blob/main/src/client.mjs#L28

  Rótuloscall-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

  Evidênciahttps://github.com/evoke-build/evoke/blob/main/crates/evoke-adapters/src/systemone.rs#L85

  Rótuloscall-site-verified

• f-tiger/jev-decision-gate

  README states: Use Jev for Issue triage without building the whole integration and review workflow.

  Evidênciahttps://github.com/f-tiger/jev-decision-gate/blob/main/skills/jev-decision-gate/scripts/jev_decision_gate/triage.py#L15

  Rótuloscall-site-verified

• f/jev-leftpad

  README states: Set TYPESAFE_API_KEY before using it. jev-leftpad uses jev-latest through

  Evidênciahttps://github.com/f/jev-leftpad/blob/main/src/index.js#L1

  Rótuloscall-site-verified

• fabricioctelles/skills

  README states: references/jev-integration.md — integration patterns and code examples

  Evidênciahttps://github.com/fabricioctelles/skills/blob/main/README.md#L49

  Rótulosreadme-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。

  Evidênciahttps://github.com/FBddcz/embodied-jev/blob/main/README.md#L42

  Rótulosreadme-claim

• featherless-ai/simple-jev

  README states: curl https://simple-jev-demo-api.featherless.ai/v1/models

  Evidênciahttps://github.com/featherless-ai/simple-jev/blob/main/README.md#L20

  Rótulosreadme-claim

• feder-cr/jev

  README states:

  Evidênciahttps://github.com/feder-cr/jev/blob/main/src/main.cpp#L166

  Rótuloscall-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.

  Evidênciahttps://github.com/FeiLiuEM/tetrajev/blob/main/scripts/run_jev_api.py#L5

  Rótuloscall-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。

  Evidênciahttps://github.com/FerryCorleone/crush-monitor/blob/main/server/analysis.ts#L7

  Rótuloscall-site-verified

• flitsinc/go-llms

  README states: TypeSafe System One models (Jev): typed judgments with probabilities, driven by a JSON output schema

  Evidênciahttps://github.com/flitsinc/go-llms/blob/main/README.md#L9

  Rótulosreadme-claim

• FluidInference/FluidUse

  README states: Jev-style decision model: a 322M mmBERT encoder plus decision head that answers typed

  Evidênciahttps://github.com/FluidInference/FluidUse/blob/main/Sources/FluidUse/PublishedCoreML/PublishedCoreMLTypes.swift#L80

  Rótuloscall-site-verified

• Foadsf/jev-for-engineers

  README states: so twelve questions in one call cost about what one call costs. TypeSafe

  Evidênciahttps://github.com/Foadsf/jev-for-engineers/blob/main/jev.py#L11

  Rótuloscall-site-verified

• FrancoisChastel/jev-code

  README states: jev-code

  Evidênciahttps://github.com/FrancoisChastel/jev-code/blob/main/README.md#L1

  Rótulosreadme-claim

• freepik-company/jev-mcp

  README states: TypeSafe's System One model, through OpenRouter or TypeSafe directly.

  Evidênciahttps://github.com/freepik-company/jev-mcp/blob/main/internal/judgment/tasks.go#L35

  Rótuloscall-site-verified

• frostney/clean-code-review

  README states: Point it at a public GitHub pull request, a diff or a file. Jev, TypeSafe's

  Evidênciahttps://github.com/frostney/clean-code-review/blob/main/README.md#L7

  Rótulosreadme-claim

• gamesonrblx/Jevbridge

  README states: ACP and MCP adapter that bridges TypeSafe Jev with any LLM.

  Evidênciahttps://github.com/gamesonrblx/Jevbridge/blob/main/src/types.ts#L111

  Rótuloscall-site-verified

• gbh1234/Adaptive-rag

  README states: INTENT_BACKEND=jev

  Evidênciahttps://github.com/gbh1234/Adaptive-rag/blob/main/README.md#L83

  Rótulosreadme-claim

• genspark-ai/genoffice

  README states: Six apps, one AI panel, a file search reranked by TypeSafe Jev, an Ask AI

  Evidênciahttps://github.com/genspark-ai/genoffice/blob/main/apps/shell/src/main/file-index/decider.ts#L52

  Rótuloscall-site-verified

• get-convex/convex-evals

  README states: bun run decisions dry-run --provider openrouter --model typesafe/jev-1.13 --limit-evals 2

  Evidênciahttps://github.com/get-convex/convex-evals/blob/main/README.md#L44

  Rótulosreadme-claim

• GhalebDweikat/winnow

  README states: winnow replay score --judged ~/.winnow/replay/judged-typesafe.jsonl

  Evidênciahttps://github.com/GhalebDweikat/winnow/blob/main/sidecar/src/winnow/hooks.py#L282

  Rótuloscall-site-verified

• GhrezaKh74/JevTicktRouter

  README states: Structured support-ticket triage built on .NET 10 and React 19, using TypeSafe Jev to make

  Evidênciahttps://github.com/GhrezaKh74/JevTicktRouter/blob/master/backend/JevTicketRouter.Infrastructure/Decisions/SelfHosted/SelfHostedOptions.cs#L42

  Rótuloscall-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

  Evidênciahttps://github.com/gi-dellav/hsom/blob/main/README.md#L5

  Rótulosreadme-claim

• githubnext/localjev

  README states: A local, Jev-compatible POST /v1/systemone API written in TypeScript for

  Evidênciahttps://github.com/githubnext/localjev/blob/main/src/server.ts#L19

  Rótuloscall-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

  Evidênciahttps://github.com/Godefroy/micdrop/blob/main/README.md#L27

  Rótulosreadme-claim

• GodsBoy/jev-agent-skill-router

  README states:

  Evidênciahttps://github.com/GodsBoy/jev-agent-skill-router/blob/main/src/jev_router/transport.py#L12

  Rótuloscall-site-verified

• gopaljigaur/decide

  README states: them through one API: TypeSafe's hosted Jev, OpenRouter, OpenAI's Decisions

  Evidênciahttps://github.com/gopaljigaur/decide/blob/main/decide/backends/typesafe.py#L20

  Rótuloscall-site-verified

• Govcraft/emergent

  README states: Judgment as a Pipeline Step: jev-handler

  Evidênciahttps://github.com/Govcraft/emergent/blob/main/README.md#L161

  Rótulosreadme-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

  Evidênciahttps://github.com/gtaras7/typesafe-jev/blob/main/cv-screen/src/cli.ts#L97

  Rótuloscall-site-verified

• GuSheng107/helpme-Jev

  README states: JEV decides. LLM explains. You decide.

  Evidênciahttps://github.com/GuSheng107/helpme-Jev/blob/main/README.md#L55

  Rótulosreadme-claim

• hamgua/alpha-trading-bot-okx

  README states: Jev 快车道（TypeSafe System One）

  Evidênciahttps://github.com/hamgua/alpha-trading-bot-okx/blob/main/README.md#L361

  Rótulosreadme-claim

• harlan-zw/harlan-agent-kit

  README states: api.typesafe.ai or the Vercel AI Gateway.

  Evidênciahttps://github.com/harlan-zw/harlan-agent-kit/blob/main/packages/advocaat/README.md#L9

  Rótulosreadme-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.

  Evidênciahttps://github.com/haseeb-heaven/jev-system-one/blob/master/src/jev_system_one/jev.py#L3

  Rótuloscall-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.

  Evidênciahttps://github.com/hatt-io/jevkeep/blob/main/README.md#L17

  Rótulosreadme-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.

  Evidênciahttps://github.com/hellogumbo/should-ai-kill-us-all/blob/main/functions/api/verdict.js#L10

  Rótuloscall-site-verified

• hellozenstrategist-lab/eutrya

  README states: A standalone terminal agent with Jev in its decision loop.

  Evidênciahttps://github.com/hellozenstrategist-lab/eutrya/blob/main/extensions/eutrya-adaptive-extension/integration/native-v02.mjs#L9

  Rótuloscall-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)

  Evidênciahttps://github.com/hemanth/is-lesion/blob/main/README.md#L48

  Rótulosreadme-claim

• hev/reranker

  README states: nDCG@10, every system permuting the same BM25 top-30 shortlist per query. Jev uses the

  Evidênciahttps://github.com/hev/reranker/blob/main/hev_rerank/rerank.py#L18

  Rótuloscall-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. |

  Evidênciahttps://github.com/heyjunpenn/awesome-jev/blob/main/README.md#L80

  Rótulosreadme-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。

  Evidênciahttps://github.com/HorusJiang/dsh-jev-tools/blob/main/README.md#L18

  Rótulosreadme-claim

• hotchpotch/jev-reranker

  README states: | model | Explicit value → JEV_MODEL (environment/.env) → jev-latest |

  Evidênciahttps://github.com/hotchpotch/jev-reranker/blob/main/README.md#L434

  Rótulosreadme-claim

• hraness/algal

  README states: or reuse a TypeSafe key. doctor --clef checks configuration without an API

  Evidênciahttps://github.com/hraness/algal/blob/main/README.md#L895

  Rótulosreadme-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.

  Evidênciahttps://github.com/hunkim/solar-mini4-jev/blob/main/engine.py#L158

  Rótuloscall-site-verified

• huntedman/JevLint

  README states: JevLint is powered by Jev, TypeSafe AI’s System One model. It sends selected source

  Evidênciahttps://github.com/huntedman/JevLint/blob/main/src/jev-client.ts#L52

  Rótuloscall-site-verified

• HyunjunJeon/jev-judgment

  README states: TypeSafe Jev and acts on the probabilities. The

  Evidênciahttps://github.com/HyunjunJeon/jev-judgment/blob/main/README.md#L6

  Rótulosreadme-claim

• iamjonatha/decisionkit-dotnet

  README states: A strongly typed, provider-independent decision engine for .NET, with TypeSafe JEV support.

  Evidênciahttps://github.com/iamjonatha/decisionkit-dotnet/blob/main/README.md#L3

  Rótulosreadme-claim

• iamtoomas/JevLint

  README states: JevLint is powered by Jev, TypeSafe AI’s System One model. It sends selected source

  Evidênciahttps://github.com/iamtoomas/JevLint/blob/main/src/jev-client.ts#L52

  Rótuloscall-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 |

  Evidênciahttps://github.com/IAmUnbounded/save-token-jev-clean/blob/main/README.md#L185

  Rótulosreadme-claim

• iamvatsalpatel/tiershift

  README states: The judgment comes from TypeSafe Jev , a calibrated decision model. About 180 ms. Four cents per thousand routes.

  Evidênciahttps://github.com/iamvatsalpatel/tiershift/blob/main/bench/experiments/gate-experiment.ts#L10

  Rótuloscall-site-verified

• iefnaf/pi-jev

  README states:

  Evidênciahttps://github.com/iefnaf/pi-jev/blob/main/README.md#L9

  Rótulosreadme-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

  Evidênciahttps://github.com/ielab/llm-rankers/blob/main/README.md#L7

  Rótulosreadme-claim

• ilyamk/jev-gmail-ai-spam-filter-and-labeling

  README states: Semantic email classification powered by Jev, with confidence-aware automation,

  Evidênciahttps://github.com/ilyamk/jev-gmail-ai-spam-filter-and-labeling/blob/main/README.md#L11

  Rótulosreadme-claim

• InternLM/Intern-Decision

  README states: Intern-Decision-4B reaches 90.02% average accuracy across seven suites (Jev: 88.74%),

  Evidênciahttps://github.com/InternLM/Intern-Decision/blob/main/README.md#L97

  Rótulosreadme-claim

• intikhab49/open-jev-typed-decision-engine

  README states:

  Evidênciahttps://github.com/intikhab49/open-jev-typed-decision-engine/blob/main/README.md#L3

  Rótulosreadme-claim

• ipenywis/laya-ultrafast

  README states: Hosted mode still works. Set DECISION_MODEL=typesafe to use the original Jev policy unchanged.

  Evidênciahttps://github.com/ipenywis/laya-ultrafast/blob/main/laya_ultrafast/laya.py#L48

  Rótuloscall-site-verified

• ItIsCuthNotCup/MetaCog

  README states: judge = SystemOneJudge.jev() # hosted; reads $TYPESAFE_API_KEY

  Evidênciahttps://github.com/ItIsCuthNotCup/MetaCog/blob/main/README.md#L48

  Rótulosreadme-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.

  Evidênciahttps://github.com/itsmostafa/typesafe-mcp/blob/main/README.md#L10

  Rótulosreadme-claim

• itsoltech/basal-rs

  README states:

  Evidênciahttps://github.com/itsoltech/basal-rs/blob/main/contracts/typesafe/README.md#L4

  Rótulosreadme-claim

• j1s4nn/duomind

  README states: Internet connection for setup and Jev API calls

  Evidênciahttps://github.com/j1s4nn/duomind/blob/main/README.md#L111

  Rótulosreadme-claim

• JamesANZ/us-legal-mcp

  README states: JEV_MODEL – default jev-latest

  Evidênciahttps://github.com/JamesANZ/us-legal-mcp/blob/main/README.md#L234

  Rótulosreadme-claim

• jamesward/zio-typesafe-ai

  README states: Jev / System One API — a "System One model" that answers typed, atomic

  Evidênciahttps://github.com/jamesward/zio-typesafe-ai/blob/main/src/main/scala/com/jamesward/zio_typesafe_ai/TypeSafeAI.scala#L3

  Rótuloscall-site-verified

• JanOstrowka/typesafe-assist

  README states:

  Evidênciahttps://github.com/JanOstrowka/typesafe-assist/blob/main/custom_components/typesafe_conversation/api.py#L161

  Rótuloscall-site-verified

• jaredpalmer/kev

  README states: Small Jev-like decision models you can train and run yourself.

  Evidênciahttps://github.com/jaredpalmer/kev/blob/main/README.md#L3

  Rótulosreadme-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.

  Evidênciahttps://github.com/jarrodwatts/jev-trader/blob/main/src/model.ts#L2

  Rótuloscall-site-verified

• jccrump/openbot

  README states: Google, Mistral, or a local model through Ollama or LM Studio. An optional Jev

  Evidênciahttps://github.com/jccrump/openbot/blob/main/README.md#L7

  Rótulosreadme-claim

• jcpsimmons/jev-macos-loop

  README states: Read https://raw.githubusercontent.com/jcpsimmons/jev-macos-loop/master/AGENTS.md

  Evidênciahttps://github.com/jcpsimmons/jev-macos-loop/blob/master/src/providers.mjs#L17

  Rótuloscall-site-verified

• JedimEmO/typesafe-client

  README states: endorsed by, or supported by TypeSafe AI. For the API itself, see the

  Evidênciahttps://github.com/JedimEmO/typesafe-client/blob/main/crates/typesafe-client/src/answer.rs#L405

  Rótuloscall-site-verified

• jerryfane/omp-jev-compaction

  README states: TypeSafe's Jev decision model, over either the TypeSafe API or OpenRouter.

  Evidênciahttps://github.com/jerryfane/omp-jev-compaction/blob/master/src/asker.ts#L21

  Rótuloscall-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

  Evidênciahttps://github.com/jev-chat/jev-chat-windows/blob/main/README.md#L47

  Rótulosreadme-claim

• jhd3197/Prompture

  README states: driver = get_decision_driver_for_model("typesafe/jev-latest")

  Evidênciahttps://github.com/jhd3197/Prompture/blob/main/prompture/drivers/kev_decision_driver.py#L4

  Rótuloscall-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

  Evidênciahttps://github.com/jkudish/jev-mcp/blob/main/README.md#L733

  Rótulosreadme-claim

• jmanhype/jev-dspy-lab

  README states: and other callers that use TypeSafe decisions inside DSPy-style pipelines.

  Evidênciahttps://github.com/jmanhype/jev-dspy-lab/blob/main/scripts/verify_integration.py#L41

  Rótuloscall-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.

  Evidênciahttps://github.com/joelhooks/pi-fast-jev-compaction/blob/main/src/core/request.ts#L8

  Rótuloscall-site-verified

• jomatsu/pi-jev-auto-mode

  README states: decision models, with Jev (TypeSafe System One) as the default. OpenAI Decisions,

  Evidênciahttps://github.com/jomatsu/pi-jev-auto-mode/blob/main/src/jev/engine.ts#L95

  Rótuloscall-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

  Evidênciahttps://github.com/jomatsu/zod-jev/blob/main/scripts/check-package.mjs#L35

  Rótuloscall-site-verified

• jonathanavis96/jev-kit

  README states: What is Jev, and why a kit

  Evidênciahttps://github.com/jonathanavis96/jev-kit/blob/main/README.md#L39

  Rótulosreadme-claim

• jozefRudy/job_search

  README states: Optional; omit either key to use the default (https://api.typesafe.ai, jev-latest).

  Evidênciahttps://github.com/jozefRudy/job_search/blob/main/README.md#L52

  Rótulosreadme-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.

  Evidênciahttps://github.com/jucelioalencar/linearmemory/blob/main/README.md#L175

  Rótulosreadme-claim

• jujumilk3/jev-calibration-audit

  README states: An independent, API-only audit of the calibration of TypeSafe AI's Jev, a

  Evidênciahttps://github.com/jujumilk3/jev-calibration-audit/blob/main/src/jev_audit/client.py#L12

  Rótuloscall-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.

  Evidênciahttps://github.com/justinhe16/trade-jev/blob/main/src/trade_jev/live.py#L993

  Rótuloscall-site-verified

• jxucoder/mimicry

  README states: and TypeSafe; requests and responses are saved locally under ignored

  Evidênciahttps://github.com/jxucoder/mimicry/blob/master/README.md#L37

  Rótulosreadme-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.

  Evidênciahttps://github.com/kavehmz/typesafe-playground/blob/main/demo01/server.mjs#L67

  Rótuloscall-site-verified

• keltokhy/jgrep

  README states: Each line becomes one yes/no question to Jev, TypeSafe's decision

  Evidênciahttps://github.com/keltokhy/jgrep/blob/main/README.md#L16

  Rótulosreadme-claim

• kesku/jev-freeform

  README states: Can TypeSafe Jev Choice generate text through successive typed decisions? Well I tried it

  Evidênciahttps://github.com/kesku/jev-freeform/blob/main/main.mjs#L172

  Rótuloscall-site-verified

• kevinbadi/jev-voice

  README states: Everything runs locally except one ~250 ms call to Jev (TypeSafe's System One

  Evidênciahttps://github.com/kevinbadi/jev-voice/blob/main/jev_voice/brain.py#L174

  Rótuloscall-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.

  Evidênciahttps://github.com/Kevthetech143/super-jev/blob/main/README.md#L9

  Rótulosreadme-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.

  Evidênciahttps://github.com/kieranklaassen/ruby_llm-typesafe/blob/main/README.md#L11

  Rótulosreadme-claim

• KiritoKing/midscene-jev-runner

  README states: The default is TypeSafe System One: POST https://api.typesafe.ai/v1/systemone

  Evidênciahttps://github.com/KiritoKing/midscene-jev-runner/blob/main/README.md#L66

  Rótulosreadme-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.

  Evidênciahttps://github.com/klauswg/jev-guard/blob/master/src/main/java/com/jevguard/client/JevClient.java#L13

  Rótuloscall-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.

  Evidênciahttps://github.com/klauswg/jev-suite/blob/master/jev-fidelity/src/main/java/com/jevsuite/fidelity/eval/EvalRunner.java#L52

  Rótuloscall-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.

  Evidênciahttps://github.com/knowlet/jevlens/blob/master/extension/lib/jev.js#L4

  Rótuloscall-site-verified

• kouhxp/gutsy

  README states: network calls, no per-call cost. The API follows the Jev-style Decisions format, so existing clients

  Evidênciahttps://github.com/kouhxp/gutsy/blob/main/gutsy-inference/gutsy_inference/server.py#L21

  Rótuloscall-site-verified

• kraayenjon/awesome-jev

  README states:

  Evidênciahttps://github.com/kraayenjon/awesome-jev/blob/main/README.md#L2

  Rótulosreadme-claim

• kshetrajna12/reflex

  README states: the "System One" model TypeSafe released in September 2026, built on top of a normal

  Evidênciahttps://github.com/kshetrajna12/reflex/blob/main/scripts/bench_latency.py#L6

  Rótuloscall-site-verified

• kyegomez/open-jev

  README states: System One Models and Jev

  Evidênciahttps://github.com/kyegomez/open-jev/blob/main/README.md#L161

  Rótulosreadme-claim

• kyu1204/jgrep

  README states: jgrep runs on Jev, through TypeSafe or

  Evidênciahttps://github.com/kyu1204/jgrep/blob/main/README.md#L41

  Rótulosreadme-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.

  Evidênciahttps://github.com/kyu1204/oh-my-harness/blob/main/src/catalog/blocks/semantic-rule-guard.ts#L68

  Rótuloscall-site-verified

• lakeday-org/perch

  README states: export PERCH_BASE_URL=https://api.typesafe.ai/v1/systemone

  Evidênciahttps://github.com/lakeday-org/perch/blob/main/.benchmarks/reviewbench/run.mjs#L15

  Rótuloscall-site-verified

• lhotwll217/jev-cli

  README states: JSON in, typed decisions out. A thin CLI over the TypeSafe System One API

  Evidênciahttps://github.com/lhotwll217/jev-cli/blob/main/src/client.ts#L25

  Rótuloscall-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.

  Evidênciahttps://github.com/Li-Evan/awesome-jev/blob/main/README.md#L468

  Rótulosreadme-claim

• libingzheren/Jev-Mem

  README states: Jev-Mem separates the frequent decisions of memory management from the deeper

  Evidênciahttps://github.com/libingzheren/Jev-Mem/blob/main/memory/jev_client.py#L23

  Rótuloscall-site-verified

• liu-x27/XavierJev

  README states: TypeSafe: nothing here calls the Jev API, and nothing was trained on its output.

  Evidênciahttps://github.com/liu-x27/XavierJev/blob/main/eval/decision-models/run.ts#L177

  Rótuloscall-site-verified

• liuyanghejerry/Clausura

  README states: model: jev-latest # Default. Decision model id.

  Evidênciahttps://github.com/liuyanghejerry/Clausura/blob/main/README.md#L330

  Rótulosreadme-claim

• luisleo526/doc2mark

  README states: TypeSafe's Jev can be asked about the cases they leave open (is this

  Evidênciahttps://github.com/luisleo526/doc2mark/blob/main/README.md#L23

  Rótulosreadme-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.

  Evidênciahttps://github.com/lykycy123/RoboJEV/blob/main/src/jev_vla_sim/config.py#L27

  Rótuloscall-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

  Evidênciahttps://github.com/lyramakesmusic/jevbot/blob/master/README.md#L11

  Rótulosreadme-claim

• maayanlevy/mysql-ailike

  README states: Requires a TypeSafe API key. Note: evaluated values and prompts are

  Evidênciahttps://github.com/maayanlevy/mysql-ailike/blob/main/src/typesafe.h#L16

  Rótuloscall-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.

  Evidênciahttps://github.com/madisonrickert/jev-permission-gate/blob/main/hooks/register.ts#L25

  Rótuloscall-site-verified

• MahmoudAdelbghany/jev-browser

  README states: one Jev call (parallel questions, ~300 ms, no LLM tokens)

  Evidênciahttps://github.com/MahmoudAdelbghany/jev-browser/blob/main/src/jev.mjs#L1

  Rótuloscall-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

  Evidênciahttps://github.com/mahynotch/newsscore/blob/main/src/newsscore/scoring/jev.py#L416

  Rótuloscall-site-verified

• maker-KK/todo-jev

  README states: A task-routing experiment powered by TypeSafe Jev, structured skill profiles, and basic environment checks.

  Evidênciahttps://github.com/maker-KK/todo-jev/blob/main/app/classifier.py#L14

  Rótuloscall-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.

  Evidênciahttps://github.com/malDuffin/typesafe-3d-chess/blob/main/README.md#L2

  Rótulosreadme-claim

• mandu5/jevcompat

  README states: About a hundred servers say they are "Jev-compatible". Nothing said what that means. Now something does.

  Evidênciahttps://github.com/mandu5/jevcompat/blob/main/README.md#L3

  Rótulosreadme-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。

  Evidênciahttps://github.com/manifoldor/xtags/blob/main/extension/service.js#L3

  Rótuloscall-site-verified

• marcreichel/laya-php

  README states: curl -fsSL https://api.typesafe.ai/openapi.json -o openapi.json

  Evidênciahttps://github.com/marcreichel/laya-php/blob/main/src/Laya.php#L197

  Rótuloscall-site-verified

• MarissaFamularo/citation-verifier

  README states: supports the sentence, and Jev's confidence in its own call. A probability

  Evidênciahttps://github.com/MarissaFamularo/citation-verifier/blob/main/README.md#L34

  Rótulosreadme-claim

• markjaquith/typesafe-ai-playground

  README states: The experiments live in a Rust CLI called typesafe-ai, built with

  Evidênciahttps://github.com/markjaquith/typesafe-ai-playground/blob/main/src/typesafe.rs#L57

  Rótuloscall-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.

  Evidênciahttps://github.com/MartinPuli/f1/blob/main/scripts/refine-prompts.mjs#L55

  Rótuloscall-site-verified

• mattn/go-jev

  README states: text. Comes with jev-cli, a command-line tool built on it for UNIX pipelines.

  Evidênciahttps://github.com/mattn/go-jev/blob/main/jev.go#L19

  Rótuloscall-site-verified

• mejiasd3v/pi-jev-router

  README states:

  Evidênciahttps://github.com/mejiasd3v/pi-jev-router/blob/main/index.ts#L407

  Rótuloscall-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。

  Evidênciahttps://github.com/memos-im/xianyu-slang-helper/blob/main/README.md#L147

  Rótulosreadme-claim

• Micha0827/snapjudge

  README states: The HTTP API follows the TypeSafe System One format

  Evidênciahttps://github.com/Micha0827/snapjudge/blob/main/README.md#L7

  Rótulosreadme-claim

• misbahsy/doc-router

  README states: Jev (TypeSafe System One) — the page judge. Given the

  Evidênciahttps://github.com/misbahsy/doc-router/blob/main/README.md#L36

  Rótulosreadme-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).

  Evidênciahttps://github.com/mithalouni/system-one-open/blob/main/README.md#L31

  Rótulosreadme-claim

• mizchi/jev-lint

  README states: export TYPESAFE_API_KEY=... # https://typesafe.ai

  Evidênciahttps://github.com/mizchi/jev-lint/blob/main/src/clef.ts#L54

  Rótuloscall-site-verified

• mizchi/jev-test-filter

  README states: jev-test-filter reads a git diff, asks a model how much that change can

  Evidênciahttps://github.com/mizchi/jev-test-filter/blob/main/src/jev.ts#L26

  Rótuloscall-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.

  Evidênciahttps://github.com/mkotlikov/jev-grug/blob/main/app/api/chat/route.ts#L30

  Rótuloscall-site-verified

• mmastrac/djev

  README states: POST /v1/systemone implements the Jev decision API. The body holds

  Evidênciahttps://github.com/mmastrac/djev/blob/main/structured_server.py#L2014

  Rótuloscall-site-verified

• mmastrac/djev-spark

  README states: it implements Jev's POST /v1/systemone API and passes ordinary chat through

  Evidênciahttps://github.com/mmastrac/djev-spark/blob/main/scripts/long-context-probe.py#L35

  Rótuloscall-site-verified

• mohsen1/llm-debugger-vscode-extension

  README states: Each step's "what next?" is answered by Jev, a

  Evidênciahttps://github.com/mohsen1/llm-debugger-vscode-extension/blob/main/README.md#L7

  Rótulosreadme-claim

• morganlinton/Albatross

  README states: Jev Mode puts TypeSafe AI's decision model before the main LLM. Supported questions

  Evidênciahttps://github.com/morganlinton/Albatross/blob/main/src/jev.rs#L13

  Rótuloscall-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

  Evidênciahttps://github.com/moritzkremb/jev-voice-browser/blob/main/src/jev.js#L7

  Rótuloscall-site-verified

• mossyfield/ST-jeved

  README states: Jeved is a SillyTavern extension. It sends chat messages to Jev, a small decision model, with

  Evidênciahttps://github.com/mossyfield/ST-jeved/blob/main/src/classifier.js#L22

  Rótuloscall-site-verified

• mrbanana55/Decision_Blackjack

  README states: Jev (Remote Cloud AI via TypeSafe System One)

  Evidênciahttps://github.com/mrbanana55/Decision_Blackjack/blob/main/README.md#L8

  Rótulosreadme-claim

• mrmps/classifier-dev

  README states: Both tiers answer from TypeSafe's Jev, a decision

  Evidênciahttps://github.com/mrmps/classifier-dev/blob/main/README.md#L128

  Rótulosreadme-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

  Evidênciahttps://github.com/n42blockchain/N42-rs/blob/main/ddn/docs/decision/README.md#L44

  Rótulosreadme-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.

  Evidênciahttps://github.com/Nainish-Rai/jev-frontend-qa/blob/main/src/jev_frontend_qa/core/model_client.py#L3

  Rótuloscall-site-verified

• Nancy-Chauhan/hearth-jev-rental-search

  README states: A TypeSafe API key. A search costs a fraction of a cent

  Evidênciahttps://github.com/Nancy-Chauhan/hearth-jev-rental-search/blob/main/README.md#L18

  Rótulosreadme-claim

• NandhaKishorM/laya

  README states: wire protocol as TypeSafe's hosted Jev API. Laya's answer payload is already

  Evidênciahttps://github.com/NandhaKishorM/laya/blob/main/laya-dotnet/tools/bench_python.py#L191

  Rótuloscall-site-verified

• Nasrallah-AL/jev-cli

  README states: Fast, typed AI judgments from the command line, powered by TypeSafe's Jev model.

  Evidênciahttps://github.com/Nasrallah-AL/jev-cli/blob/main/README.md#L8

  Rótulosreadme-claim

• nassim-arifette/jevgrep

  README states: authorized repository, asks Jev to score all eligible fragments, then returns the

  Evidênciahttps://github.com/nassim-arifette/jevgrep/blob/main/experiments/jev-contract/offline-worker.mjs#L4

  Rótuloscall-site-verified

• ndolinschi/harnessjudge

  README states: After an agent step (paste a trace) → ok / retry / escalate / stop — for agent builders, powered by TypeSafe Jev.

  Evidênciahttps://github.com/ndolinschi/harnessjudge/blob/main/src/app/api/decide/route.ts#L7

  Rótuloscall-site-verified

• ndolinschi/pulselane

  README states: Clinic triage decisions powered by TypeSafe Jev (System One).

  Evidênciahttps://github.com/ndolinschi/pulselane/blob/main/src/app/api/decide/route.ts#L9

  Rótuloscall-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.

  Evidênciahttps://github.com/ndolinschi/toolgate/blob/main/src/app/api/decide/route.ts#L9

  Rótuloscall-site-verified

• newfull5/malkuth

  README states: suites and about 129,000 questions. Every model answered the same items. Jev was measured through its API.

  Evidênciahttps://github.com/newfull5/malkuth/blob/main/tools/laya_bench.py#L27

  Rótuloscall-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.

  Evidênciahttps://github.com/NiazMorshed2007/jev-review/blob/main/src/jev/client.ts#L4

  Rótuloscall-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.

  Evidênciahttps://github.com/nican2018/shade-arena-jev-monitor/blob/main/llms/typesafe_llm.py#L20

  Rótuloscall-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:

  Evidênciahttps://github.com/nicobailon/pi-powerline-footer/blob/main/README.md#L329

  Rótulosreadme-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)

  Evidênciahttps://github.com/nicobailon/surf-cli/blob/main/native/semantic-cli.cjs#L632

  Rótuloscall-site-verified

• nidhi-singh02/agent-router

  README states: shared accounts), asks TypeSafe to rank what is left and choose an effort, starts the chosen

  Evidênciahttps://github.com/nidhi-singh02/agent-router/blob/main/packages/router/src/commands/effort.ts#L264

  Rótuloscall-site-verified

• Nisaka520/JevIntent

  README states: POST https://api.typesafe.ai/v1/systemone：

  Evidênciahttps://github.com/Nisaka520/JevIntent/blob/main/README.md#L232

  Rótulosreadme-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.

  Evidênciahttps://github.com/NobleSpartan6/otto/blob/main/core/typesafe.ts#L4

  Rótuloscall-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.

  Evidênciahttps://github.com/noetion/dsh-jev/blob/main/src/client.ts#L10

  Rótuloscall-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.

  Evidênciahttps://github.com/NorbertBodziony/guard-jev/blob/main/app/api/moderate/route.ts#L2

  Rótuloscall-site-verified

• notque/vexjoy-agent

  README states: /d — Jev-Powered Router

  Evidênciahttps://github.com/notque/vexjoy-agent/blob/main/README.md#L44

  Rótulosreadme-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.

  Evidênciahttps://github.com/ntedvs/commentcop/blob/main/src/judge.ts#L1

  Rótuloscall-site-verified

• Nyarlathoteppppp/pi-heed

  README states: messages, 9,090 real tool calls) through pi-heed in enforce mode with Jev, without executing anything

  Evidênciahttps://github.com/Nyarlathoteppppp/pi-heed/blob/main/src/judge.ts#L53

  Rótuloscall-site-verified

• obie/ruby_decision_model

  README states: Requests go to https://api.typesafe.ai/v1/systemone. The default model is

  Evidênciahttps://github.com/obie/ruby_decision_model/blob/main/README.md#L85

  Rótulosreadme-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

  Evidênciahttps://github.com/oficcejo/aiagents-stock/blob/main/README.md#L170

  Rótulosreadme-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.

  Evidênciahttps://github.com/ojusave/beat-jev/blob/main/python/app/keeper.py#L2

  Rótuloscall-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.

  Evidênciahttps://github.com/Olli0103/openclaw-typesafe-ai/blob/main/src/client.ts#L4

  Rótuloscall-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

  Evidênciahttps://github.com/olsenbrands/fable-foreman/blob/main/README.md#L11

  Rótulosreadme-claim

• OmniJev/OneJev

  README states:

  Evidênciahttps://github.com/OmniJev/OneJev/blob/main/qev/cli.py#L143

  Rótuloscall-site-verified

• ondata/vd-jev

  README states: Ask three questions about the message column, one jev-column each:

  Evidênciahttps://github.com/ondata/vd-jev/blob/main/README.md#L55

  Rótulosreadme-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:

  Evidênciahttps://github.com/onlyoneaman/jev-eval/blob/main/jev_eval/backends.py#L16

  Rótuloscall-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:

  Evidênciahttps://github.com/opencx-labs/zevals/blob/main/README.md#L273

  Rótulosreadme-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.

  Evidênciahttps://github.com/openlayer-ai/jevals/blob/main/src/jevals/backends/_base.py#L65

  Rótuloscall-site-verified

• OskarLebuda/precog

  README states: Asks TypeSafe Jev which link a visitor is about to click, then warms

  Evidênciahttps://github.com/OskarLebuda/precog/blob/main/README.md#L19

  Rótulosreadme-claim

• oso95/x-scanner

  README states: Behavioral labels on every post you scroll past on X, judged by Jev,

  Evidênciahttps://github.com/oso95/x-scanner/blob/main/README.md#L3

  Rótulosreadme-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.

  Evidênciahttps://github.com/PanAchy/jevvy/blob/main/packages/core/src/system-one.ts#L12

  Rótuloscall-site-verified

• pavy23/web-doom

  README states: Tactical policy (TypeSafe System One, Jev). At each step with an enemy

  Evidênciahttps://github.com/pavy23/web-doom/blob/main/README.md#L288

  Rótulosreadme-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。

  Evidênciahttps://github.com/pengchujin/ad-radar/blob/main/README.md#L6

  Rótulosreadme-claim

• PerryLink/jevcore

  README states: TypeSafe Jev for DeepSeek Harness

  Evidênciahttps://github.com/PerryLink/jevcore/blob/main/README.md#L8

  Rótulosreadme-claim

• peterfriese/system-one-foundation-models

  README states: Jev Cloud: TypeSafe AI hosted service on https://api.typesafe.ai.

  Evidênciahttps://github.com/peterfriese/system-one-foundation-models/blob/main/README.md#L364

  Rótulosreadme-claim

• philippdubach/pi-jev-router

  README states: pi-jev-router is a pi extension. It classifies each task with Jev (TypeSafe

  Evidênciahttps://github.com/philippdubach/pi-jev-router/blob/main/src/classifier.ts#L13

  Rótuloscall-site-verified

• picaye/jev-compaction

  README states: Jev judges to be stale, and it shows Jev the whole conversation while deciding.

  Evidênciahttps://github.com/picaye/jev-compaction/blob/main/README.md#L19

  Rótulosreadme-claim

• PistachioAIHQ/jev-synergy-screening

  README states: export TYPESAFE_API_KEY="$(tr -d ' ' < ~/.config/typesafe/api_key)"

  Evidênciahttps://github.com/PistachioAIHQ/jev-synergy-screening/blob/main/src/config.py#L43

  Rótuloscall-site-verified

• pithings/advocaat

  README states: Requests use https://ai-gateway.vercel.sh/v4/ai and model typesafe-ai/jev.

  Evidênciahttps://github.com/pithings/advocaat/blob/main/src/api.ts#L127

  Rótuloscall-site-verified

• PixelML/av

  README states: Configure a TypeSafe System One key to make Jev refinement automatic for av ask:

  Evidênciahttps://github.com/PixelML/av/blob/main/README.md#L35

  Rótulosreadme-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

  Evidênciahttps://github.com/pnthn-ai/polar_llama/blob/main/README.md#L22

  Rótulosreadme-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

  Evidênciahttps://github.com/PromptEngineer48/laya-vs-jev-arena/blob/main/server.py#L29

  Rótuloscall-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,

  Evidênciahttps://github.com/psyb0t/aigate/blob/main/README.md#L179

  Rótulosreadme-claim

• PyModel/jev-judge-mcp

  README states: uvx --from 'jev-judge-mcp[typesafe]' jev-judge-mcp setup

  Evidênciahttps://github.com/PyModel/jev-judge-mcp/blob/main/evals/confinement/broker.py#L16

  Rótuloscall-site-verified

• qddegtya/qualm

  README states: Jev is the model. This is what qualm adds on top of calling its HTTP API yourself.

  Evidênciahttps://github.com/qddegtya/qualm/blob/main/README.md#L25

  Rótulosreadme-claim

• qkal/Canny

  README states: Jev

  Evidênciahttps://github.com/qkal/Canny/blob/main/README.md#L155

  Rótulosreadme-claim

• QuentinDanblon/pi-fast-jev-compaction

  README states: anything. It asks Jev, over the whole conversation, whether each old tool call and each

  Evidênciahttps://github.com/QuentinDanblon/pi-fast-jev-compaction/blob/main/index.ts#L206

  Rótuloscall-site-verified

• Query-farm/vgi-typesafe

  README states:

  Evidênciahttps://github.com/Query-farm/vgi-typesafe/blob/main/vgi_typesafe/mock_server.py#L39

  Rótuloscall-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.

  Evidênciahttps://github.com/r-ms/mini-jev/blob/main/README.md#L3

  Rótulosreadme-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

  Evidênciahttps://github.com/RafalWilinski/vibecheck/blob/main/README.md#L3

  Rótulosreadme-claim

• rajivkuriakose/typesafe-jev-examples

  README states: TypeSafe's direct API is behind an early-access waitlist. OpenRouter serves the

  Evidênciahttps://github.com/rajivkuriakose/typesafe-jev-examples/blob/main/src/jevx/client.py#L17

  Rótuloscall-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.

  Evidênciahttps://github.com/ranjan2829/AskJev/blob/main/mcp/src/jev-client.ts#L16

  Rótuloscall-site-verified

• RayenMlayeh/jevcrawl

  README states: | TYPESAFE_API_KEY | Jev API key (required) | none |

  Evidênciahttps://github.com/RayenMlayeh/jevcrawl/blob/main/README.md#L202

  Rótulosreadme-claim

• rbalch/typesafeai-review

  README states: slices the diff, asks Jev (TypeSafe's System One model) narrow typed questions per hunk,

  Evidênciahttps://github.com/rbalch/typesafeai-review/blob/master/README.md#L4

  Rótulosreadme-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).

  Evidênciahttps://github.com/rchovatiya88/cyber-breach-jev/blob/main/backend/bot_pilot.py#L50

  Rótuloscall-site-verified

• reachjalil/jevlogs

  README states:

  Evidênciahttps://github.com/reachjalil/jevlogs/blob/main/README.md#L2

  Rótulosreadme-claim

• ReallyArtificial/stuntdouble

  README states: Find out whether a local decision model can replace Jev on your traffic before you switch.

  Evidênciahttps://github.com/ReallyArtificial/stuntdouble/blob/main/sidecars/kev-space.mjs#L42

  Rótuloscall-site-verified

• realZachi/pg-jev

  README states:

  Evidênciahttps://github.com/realZachi/pg-jev/blob/master/README.md#L2

  Rótulosreadme-claim

• realZachi/typesafe-adblock

  README states: BYOK: bring your own key. There is no backend. You paste your own TypeSafe API key

  Evidênciahttps://github.com/realZachi/typesafe-adblock/blob/main/src/typesafe.js#L5

  Rótuloscall-site-verified

• receptron/laya

  README states: implementation (RLAgent.system_one) and as TypeSafe Jev's system_one API, and the output

  Evidênciahttps://github.com/receptron/laya/blob/main/README.md#L15

  Rótulosreadme-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.

  Evidênciahttps://github.com/reinhard-z/vision-jev/blob/main/README.md#L24

  Rótulosreadme-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.

  Evidênciahttps://github.com/RenaGao/jev-dataops/blob/main/jev_dataops/jev.py#L23

  Rótuloscall-site-verified

• rohanarun/computer-use-cache

  README states: Set your own TypeSafe API key to enable JEV in either server:

  Evidênciahttps://github.com/rohanarun/computer-use-cache/blob/main/server.py#L85

  Rótuloscall-site-verified

• rokbenko/quackd

  README states: quackd run arm-grip-check --robot arm-01 --by-hand --decision-llm jev --decision-mode shadow

  Evidênciahttps://github.com/rokbenko/quackd/blob/main/quackd/agent/decision/systemone.py#L100

  Rótuloscall-site-verified

• RomanSlack/jev-drone

  README states: jev-drone

  Evidênciahttps://github.com/RomanSlack/jev-drone/blob/main/README.md#L1

  Rótulosreadme-claim

• romeromarcelo/jev-retrieval

  README states:

  Evidênciahttps://github.com/romeromarcelo/jev-retrieval/blob/main/src/jev/client.rs#L28

  Rótuloscall-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

  Evidênciahttps://github.com/rorshopping/jev-on-a-laptop/blob/main/README.md#L103

  Rótulosreadme-claim

• runta-dev/jot

  README states: 

  Evidênciahttps://github.com/runta-dev/jot/blob/main/README.md#L19

  Rótulosreadme-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.

  Evidênciahttps://github.com/rupeshpoojary9/poorjev/blob/main/crossbench/jev_client.py#L8

  Rótuloscall-site-verified

• ryana/jevify

  README states: TypeSafe introduction

  Evidênciahttps://github.com/ryana/jevify/blob/main/README.md#L15

  Rótulosreadme-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.

  Evidênciahttps://github.com/safzanpirani/pi-jev-skill-picker/blob/master/extensions/jev.ts#L12

  Rótuloscall-site-verified

• samdotmak/jev-recall

  README states: Jev Recall gives you LLM re-ranker quality retreival at semantic search prices and speed

  Evidênciahttps://github.com/samdotmak/jev-recall/blob/main/web/lib/systems.ts#L146

  Rótuloscall-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?*

  Evidênciahttps://github.com/samtay32/jev-system-architect/blob/main/README.md#L3

  Rótulosreadme-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.

  Evidênciahttps://github.com/santos-sanz/jev-audio-beeper/blob/main/index.ts#L1

  Rótuloscall-site-verified

• savka777/jev-use

  README states:

  Evidênciahttps://github.com/savka777/jev-use/blob/main/Sources/JevCore/Decision.swift#L177

  Rótuloscall-site-verified

• schwarzschlyle/immune

  README states: export TYPESAFE_API_KEY=... # TypeSafe Jev, which Immune asks about each call

  Evidênciahttps://github.com/schwarzschlyle/immune/blob/main/src/immune/sensing/jev.py#L15

  Rótuloscall-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

  Evidênciahttps://github.com/scienthoon/jev-ood-calibration/blob/main/README.md#L39

  Rótulosreadme-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.

  Evidênciahttps://github.com/sdras/system-one-explainer/blob/main/README.md#L31

  Rótulosreadme-claim

• SeeAPI/awesome-jev-use-cases

  README states:

  Evidênciahttps://github.com/SeeAPI/awesome-jev-use-cases/blob/main/recipes/model-routing/run.py#L14

  Rótuloscall-site-verified

• sgzmd/rss-morning

  README states: Jev classification on cheap RSS metadata (TypeSafe System One)

  Evidênciahttps://github.com/sgzmd/rss-morning/blob/main/README.md#L16

  Rótulosreadme-claim

• shaharia-lab/jev-cli

  README states:

  Evidênciahttps://github.com/shaharia-lab/jev-cli/blob/main/crates/jev-cli/src/help/docs.rs#L813

  Rótuloscall-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.

  Evidênciahttps://github.com/shamazharikh/qwen-rlcd/blob/main/README.md#L160

  Rótulosreadme-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.

  Evidênciahttps://github.com/shantanugoel/ask-jev-skill/blob/main/scripts/askjev.py#L15

  Rótuloscall-site-verified

• shantanugoel/mario-jev

  README states: Jev receives structured RAM observations and answers focused questions about movement, starting a jump, and sustaining

  Evidênciahttps://github.com/shantanugoel/mario-jev/blob/main/src/mario_jev/policy.py#L3

  Rótuloscall-site-verified

• sharziki/semdecide

  README states: Typed semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev.

  Evidênciahttps://github.com/sharziki/semdecide/blob/main/src/reflex_guard/cli.py#L180

  Rótuloscall-site-verified

• shhivv/arc-cua

  README states: not use decision models, JEV or TypeSafe; it is a standalone driver.

  Evidênciahttps://github.com/shhivv/arc-cua/blob/master/src/arc_cua/policies/typesafe.py#L26

  Rótuloscall-site-verified

• shinshin86/aituber-onair

  README states: | typesafe | TypeSafe AI | jev-latest | https://api.typesafe.ai/v1/systemone |

  Evidênciahttps://github.com/shinshin86/aituber-onair/blob/main/packages/comment-intelligence/README.md#L291

  Rótulosreadme-claim

• shitianfang/jev-use

  README states: hand the tasks that need no text output to Jev — faster steps, fewer

  Evidênciahttps://github.com/shitianfang/jev-use/blob/main/README.md#L7

  Rótulosreadme-claim

• shivendrasoni/vector-cache

  README states: The default judge is TypeSafe Jev (vendor-quoted ~100 ms per call).

  Evidênciahttps://github.com/shivendrasoni/vector-cache/blob/main/README.md#L98

  Rótulosreadme-claim

• ShuhanSun/jev-oas-sentinel

  README states: jev-oas-sentinel compares two OpenAPI documents in two layers:

  Evidênciahttps://github.com/ShuhanSun/jev-oas-sentinel/blob/main/src/jev_oas_sentinel/jev.py#L19

  Rótuloscall-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.

  Evidênciahttps://github.com/sileod/tasksource/blob/main/README.md#L76

  Rótulosreadme-claim

• socai-io/jev-social

  README states:

  Evidênciahttps://github.com/socai-io/jev-social/blob/main/src/classifier.js#L222

  Rótuloscall-site-verified

• sonnylazuardi/superterminal

  README states: The ranking comes from Jev,

  Evidênciahttps://github.com/sonnylazuardi/superterminal/blob/main/README.md#L58

  Rótulosreadme-claim

• sorrycc/typesafe-snake

  README states: TypeSafe's Jev (a System One decision model, not an LLM) plays Snake in real time.

  Evidênciahttps://github.com/sorrycc/typesafe-snake/blob/master/server/index.ts#L2

  Rótuloscall-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.

  Evidênciahttps://github.com/sosopop/jev_stock/blob/main/jev_hk_predict.py#L29

  Rótuloscall-site-verified

• SoundBlaster/Jev4Mellea

  README states: A small Python adapter that brings TypeSafe Jev's semantic checks into

  Evidênciahttps://github.com/SoundBlaster/Jev4Mellea/blob/main/src/mellea_jev/providers/categorical.py#L45

  Rótuloscall-site-verified

• SREGym/SREGym

  README states: Jev is disabled by default. To enable it for Codex, set TYPESAFE_API_KEY and run:

  Evidênciahttps://github.com/SREGym/SREGym/blob/main/clients/jev/client.py#L14

  Rótuloscall-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.

  Evidênciahttps://github.com/sriganesh/jevibe-check/blob/main/extension/background.js#L133

  Rótuloscall-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.

  Evidênciahttps://github.com/steven-shoemaker/hunch/blob/main/src/hunch/client.py#L37

  Rótuloscall-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.

  Evidênciahttps://github.com/steven-shoemaker/hunch-js/blob/main/src/client.ts#L1

  Rótuloscall-site-verified

• STRML/omp-jevens-classifier

  README states: Jev-judged permission checks for OMP's bash tool, and for eval payloads that spawn

  Evidênciahttps://github.com/STRML/omp-jevens-classifier/blob/main/jev.ts#L64

  Rótuloscall-site-verified

• sufianetaouil/every

  README states: every needs a Jev API key. If you don't have one, join the hosted-tier waitlist:

  Evidênciahttps://github.com/sufianetaouil/every/blob/main/every/judge.py#L16

  Rótuloscall-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.

  Evidênciahttps://github.com/sumleo/prompt2jev/blob/main/skills/prompt2jev/scripts/prompt2jev.py#L27

  Rótuloscall-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

  Evidênciahttps://github.com/superagents-lab/jev-search/blob/main/README.md#L5

  Rótulosreadme-claim

• supercorp-ai/supercov

  README states: export TYPESAFE_API_KEY=... # get one at https://typesafe.ai

  Evidênciahttps://github.com/supercorp-ai/supercov/blob/main/crates/supercov-cli/src/quality/tests.rs#L2768

  Rótuloscall-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.

  Evidênciahttps://github.com/szczyglis-dev/py-gpt/blob/master/src/pygpt_net/plugin/jev/worker.py#L106

  Rótuloscall-site-verified

• tacticocc/Jevbridge

  README states: ACP and MCP adapter that bridges TypeSafe Jev with any LLM.

  Evidênciahttps://github.com/tacticocc/Jevbridge/blob/main/src/types.ts#L111

  Rótuloscall-site-verified

• tamnd/kime

  README states: The base URL defaults to http://127.0.0.1:8000 in place of https://api.typesafe.ai.

  Evidênciahttps://github.com/tamnd/kime/blob/main/ts/README.md#L22

  Rótulosreadme-claim

• tanghaojin/x-smart-tags

  README states: 扩展通过 Background Service Worker 直接调用 https://api.typesafe.ai/v1/systemone。

  Evidênciahttps://github.com/tanghaojin/x-smart-tags/blob/main/README.md#L42

  Rótulosreadme-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.

  Evidênciahttps://github.com/tanxarx/awesome-jev/blob/main/README.md#L3

  Rótulosreadme-claim

• TauricResearch/TradingAgents

  README states: export TYPESAFE_API_KEY=... # Jev social-post screening (optional)

  Evidênciahttps://github.com/TauricResearch/TradingAgents/blob/main/tradingagents/agents/post_screen.py#L68

  Rótuloscall-site-verified

• tbdavid2019/ai-hedge-fund-API

  README states: Fallback Tier-3: TypeSafe Official Service (https://api.typesafe.ai/v1/systemone)

  Evidênciahttps://github.com/tbdavid2019/ai-hedge-fund-API/blob/main/README.md#L57

  Rótulosreadme-claim

• The-Vibe-Company/quivr

  README states: That is far under Jev's budget of 32k tokens for the state plus the longest

  Evidênciahttps://github.com/The-Vibe-Company/quivr/blob/main/plugins/alerts/README.md#L292

  Rótulosreadme-claim

• TholeG/typesafe-chess

  README states: Two virtual chess players, both powered by TypeSafe's System One model Jev.

  Evidênciahttps://github.com/TholeG/typesafe-chess/blob/main/README.md#L3

  Rótulosreadme-claim

• TianyuCodings/JevHarness

  README states: | docs/ | Task authoring, a recorded Jev call, comparison video, and website screenshots |

  Evidênciahttps://github.com/TianyuCodings/JevHarness/blob/main/README.md#L212

  Rótulosreadme-claim

• timpratim/macbrow

  README states: LiveKit Agents for the voice loop, TypeSafe's Jev

  Evidênciahttps://github.com/timpratim/macbrow/blob/main/README.md#L26

  Rótulosreadme-claim

• tinyhumansai/opencompany

  README states: asked of Jev — TypeSafe's System One routing model — through the TinyHumans

  Evidênciahttps://github.com/tinyhumansai/opencompany/blob/main/README.md#L114

  Rótulosreadme-claim

• TKY-27/JevSlop

  README states: Eight atomic detail Score questions plus a Jev overall Score and choice in one systemOne request.

  Evidênciahttps://github.com/TKY-27/JevSlop/blob/main/functions/api/evaluate.ts#L1

  Rótuloscall-site-verified

• togethercomputer/tev1

  README states: Jev-inspired implementation and does not use Jev's answers as training labels.

  Evidênciahttps://github.com/togethercomputer/tev1/blob/main/README.md#L102

  Rótulosreadme-claim

• TokenTrim/jev-routing-experiment

  README states: Jev is not a text model. It returns typed decisions (Choice / Score / Noul) with calibrated

  Evidênciahttps://github.com/TokenTrim/jev-routing-experiment/blob/main/jev_router/jev.py#L17

  Rótuloscall-site-verified

• tonone-ai/tonone

  README states: | JEV_API_KEY or TYPESAFE_API_KEY | https://api.typesafe.ai/v1/systemone | jev-latest | jev |

  Evidênciahttps://github.com/tonone-ai/tonone/blob/main/lib/jev/README.md#L220

  Rótulosreadme-claim

• tonsky/tgadmin

  README states: With Jev

  Evidênciahttps://github.com/tonsky/tgadmin/blob/main/README.md#L8

  Rótulosreadme-claim

• tpaulshippy/shady-town

  README states: Decisions and thresholds stay in code. Built on TypeSafe's Jev via

  Evidênciahttps://github.com/tpaulshippy/shady-town/blob/main/README.md#L88

  Rótulosreadme-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. |

  Evidênciahttps://github.com/trancong12102/agentskills/blob/main/README.md#L38

  Rótulosreadme-claim

• trpc-group/trpc-agent-go

  README states: For Jev, set JEV_BASE_URL=https://api.typesafe.ai, configure JEV_API_KEY

  Evidênciahttps://github.com/trpc-group/trpc-agent-go/blob/main/internal/systemone/README.md#L63

  Rótulosreadme-claim

• truespar/sentio

  README states: provider = "jev"

  Evidênciahttps://github.com/truespar/sentio/blob/main/README.md#L998

  Rótulosreadme-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

  Evidênciahttps://github.com/turenlabs/turenos/blob/main/command-guard/README.md#L41

  Rótulosreadme-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.

  Evidênciahttps://github.com/tyler-dot-earth/patdown/blob/main/scripts/probe-jev-input-size.mjs#L25

  Rótuloscall-site-verified

• tylergibbs1/sift

  README states: Load dist/ as an unpacked extension in chrome://extensions, then enter your TypeSafe API key on

  Evidênciahttps://github.com/tylergibbs1/sift/blob/main/scripts/smoke.ts#L74

  Rótuloscall-site-verified

• tylerjharden/ailerix

  README states: POST /api/v1/systemone — Jev-compatible Choice / Score / Noul API

  Evidênciahttps://github.com/tylerjharden/ailerix/blob/main/src/components/playground-client.tsx#L45

  Rótuloscall-site-verified

• typakon4/jev-layer

  README states:

  Evidênciahttps://github.com/typakon4/jev-layer/blob/main/src/providers/demo.mjs#L36

  Rótuloscall-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

  Evidênciahttps://github.com/TypeLLM/TypeLLM/blob/main/README.md#L48

  Rótulosreadme-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.

  Evidênciahttps://github.com/TypeSafeAI/typesafe-playground/blob/main/lib/serverJev.ts#L52

  Rótuloscall-site-verified

• UditAkhourii/quicksilver

  README states: Jev, TypeSafe's System One model. Jev returns typed

  Evidênciahttps://github.com/UditAkhourii/quicksilver/blob/main/README.md#L21

  Rótulosreadme-claim

• uehaj/sys1grep

  README states: sys1grep: endpoint api.typesafe.ai/v1/systemone (default), model jev-latest (default)

  Evidênciahttps://github.com/uehaj/sys1grep/blob/main/README.md#L229

  Rótulosreadme-claim

• uezo/aiavatarkit

  README states: Gates — Smart Turn, Namo Turn, Jev, OpenAI Decisions, LLM turn gate, filler-only, session hold, custom gates

  Evidênciahttps://github.com/uezo/aiavatarkit/blob/main/aiavatar/sts/vad/turn_end_gates/jev.py#L172

  Rótuloscall-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.

  Evidênciahttps://github.com/unownone/jevsume/blob/main/readme.md#L3

  Rótulosreadme-claim

• uu889/laya-opencv

  README states: | TypeSafe 官方 | https://api.typesafe.ai | TypeSafe 控制台的密钥 |

  Evidênciahttps://github.com/uu889/laya-opencv/blob/main/README.md#L386

  Rótulosreadme-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.

  Evidênciahttps://github.com/v-modal/awesome-jev-tools/blob/main/README.md#L7

  Rótulosreadme-claim

• valentynkit/awesome-jev-typesafe

  README states:

  Evidênciahttps://github.com/valentynkit/awesome-jev-typesafe/blob/main/scripts/jev-client.mjs#L5

  Rótuloscall-site-verified

• valentynkit/jev-commit

  README states: that the two agree. This does, in one call to Jev, before the commit lands.

  Evidênciahttps://github.com/valentynkit/jev-commit/blob/main/jev_commit/jev.py#L18

  Rótuloscall-site-verified

• valentynkit/jev-skip

  README states: Gateway shim rather than the direct API. Re-measure on api.typesafe.ai before pinning

  Evidênciahttps://github.com/valentynkit/jev-skip/blob/main/README.md#L19

  Rótulosreadme-claim

• vinilana/live-jev

  README states: TypeSafe's Jev (a "System One" decision model)

  Evidênciahttps://github.com/vinilana/live-jev/blob/main/README.md#L4

  Rótulosreadme-claim

• vnmoorthy/siege

  README states: Built at CoreWeave Hacks: Agent Loops (Weights & Biases, AGI House, TypeSafe AI), San Francisco, September 13 to 14, 2026.

  Evidênciahttps://github.com/vnmoorthy/siege/blob/main/README.md#L248

  Rótulosreadme-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

  Evidênciahttps://github.com/w3cj/jev-chat/blob/main/apps/server/src/jev/client.ts#L1

  Rótuloscall-site-verified

• walidboulanouar/awesome-jev-use-cases

  README states:

  Evidênciahttps://github.com/walidboulanouar/awesome-jev-use-cases/blob/main/README.md#L2

  Rótulosreadme-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 |

  Evidênciahttps://github.com/waynesutton/ask-jev-ai/blob/main/README.md#L40

  Rótulosreadme-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.

  Evidênciahttps://github.com/WeSecureYou/Jev-test/blob/main/src/services/jevClient.ts#L9

  Rótuloscall-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.

  Evidênciahttps://github.com/wfzyx/von/blob/master/js/src/client.ts#L10

  Rótuloscall-site-verified

• whyashthakker/awesome-jev-use-cases

  README states: git clone https://github.com/whyashthakker/awesome-jev-use-cases.git

  Evidênciahttps://github.com/whyashthakker/awesome-jev-use-cases/blob/main/shared/providers.js#L16

  Rótuloscall-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.

  Evidênciahttps://github.com/Wizhill05/typesafe-image-diffusion/blob/main/fix_synthesizer.py#L3

  Rótuloscall-site-verified

• wobsoriano/is-jeven

  README states: Uses TypeSafe AI's Jev model under the hood to determine if a number is even.

  Evidênciahttps://github.com/wobsoriano/is-jeven/blob/main/index.js#L19

  Rótuloscall-site-verified

• wustep/jev-playground

  README states: npm test # vitest: renderer invariants, Jev request shapes, proxy, MIDI round-trip, inbox/match stubs

  Evidênciahttps://github.com/wustep/jev-playground/blob/main/server/jevHandler.ts#L20

  Rótuloscall-site-verified

• Xiaooolong/vev

  README states: the official Jev API (shape reference, costs a few cents)

  Evidênciahttps://github.com/Xiaooolong/vev/blob/main/conformance/README.md#L17

  Rótulosreadme-claim

• xinyao27/jevonian

  README states: Jev picks the route for jevonian/auto — model and thinking depth in a single call.

  Evidênciahttps://github.com/xinyao27/jevonian/blob/main/internal/brain/types.go#L45

  Rótuloscall-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 |

  Evidênciahttps://github.com/xiwan/acp-bridge/blob/main/README.md#L48

  Rótulosreadme-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

  Evidênciahttps://github.com/y0usaf/pi-jev/blob/main/README.md#L145

  Rótulosreadme-claim

• yairshy/decido

  README states: ordinary Python. Start with Jev or supply your own decision provider.

  Evidênciahttps://github.com/yairshy/decido/blob/main/src/decido/providers/typesafe.py#L111

  Rótuloscall-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「

  Evidênciahttps://github.com/yan-labs/yan-skills/blob/main/agent-fleet/README.md#L123

  Rótulosreadme-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

  Evidênciahttps://github.com/Yifan-Lan/awesome-jev-robustness/blob/main/README.md#L5

  Rótulosreadme-claim

• Yinsongxu/LLM2Jev

  README states: Turn your LLM / MLLM into a Jev-style decision model. Zero training required.

  Evidênciahttps://github.com/Yinsongxu/LLM2Jev/blob/main/demos/web/server.py#L19

  Rótuloscall-site-verified

• ZeroGold/call-coach-ai

  README states: You need a TypeSafe API key. There are three ways to run Call Coach:

  Evidênciahttps://github.com/ZeroGold/call-coach-ai/blob/main/lib/coach.mjs#L13

  Rótuloscall-site-verified

• ZeroTang05/VideoAdGuard

  README states: | TypeSafe | https://api.typesafe.ai/v1 | jev-latest | 官方接口 |

  Evidênciahttps://github.com/ZeroTang05/VideoAdGuard/blob/main/README.md#L138

  Rótulosreadme-claim

• zhengxuyu/litjev

  README states: A reproduction of Jev: turn any Qwen model into a fast decision model.

  Evidênciahttps://github.com/zhengxuyu/litjev/blob/main/scripts/dump_prompt.py#L10

  Rótuloscall-site-verified

• zhuyansen/jev-search-rerank-eval

  README states: Does a TypeSafe Jev rerank beat embedding search? Measured, with the judge-bias removed.

  Evidênciahttps://github.com/zhuyansen/jev-search-rerank-eval/blob/main/README.md#L3

  Rótulosreadme-claim

• zsavage8/padflow-jev-evals

  README states: them. It exists so a decision model (TypeSafe Jev, or anything else) can be

  Evidênciahttps://github.com/zsavage8/padflow-jev-evals/blob/main/scripts/run_baseline.py#L7

  Rótuloscall-site-verified