JevCode /Retour à la couverture / Autres listes

Autres listes

425 entrées dans cette catégorie. Chacune nomme la décision concrète et renvoie à une preuve ouvrable.

• 0x7067/claude-jev

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

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

  Étiquettesreadme-claim

• 0xArx/jevegis

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

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

  Étiquettescall-site-verified

• 0xBakeer/arbiter

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

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

  Étiquettescall-site-verified

• 0xNatoshi/jev-codex-router

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

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

  Étiquettescall-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.

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

  Étiquettescall-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.

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

  Étiquettesreadme-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.

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

  Étiquettescall-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

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

  Étiquettescall-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.

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• abe75ch/tiltmeter

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

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

  Étiquettescall-site-verified

• AboveColin/HA-Jev

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

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

  Étiquettesreadme-claim

• ad-si/cai

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

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

  Étiquettesreadme-claim

• adarshmishra07/jcm-router

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• affirmitv/ghosthands

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

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

  Étiquettesreadme-claim

• afshinm/laya-mps

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

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

  Étiquettesreadme-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。

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

  Étiquettesreadme-claim

• ai4curation/jevotron

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

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

  Étiquettesreadme-claim

• AiPersonacademy/jev-resume-disqualifier

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

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

  Étiquettescall-site-verified

• alexj11324/open-jev-approvals

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

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

  Étiquettescall-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,

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

  Étiquettescall-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.

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

  Étiquettesreadme-claim

• alterhq/typesafe-sdk-swift

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

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

  Étiquettescall-site-verified

• altryne/jevify

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• andududu/jeview

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

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

  Étiquettesreadme-claim

• Anil-matcha/awesome-jev-by-typesafe

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

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

  Étiquettesreadme-claim

• aniruddh-krovvidi/switchboard

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

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

  Étiquettescall-site-verified

• anishfn/shapeshift

  README states:

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

  Étiquettescall-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.

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

  Étiquettesreadme-claim

• AntonioCoppe/jev-harness

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

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

  Étiquettescall-site-verified

• AppitStudio/awesome-jev

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

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

  Étiquettesreadme-claim

• AppSprout-dev/Unsga3

  README states: TypeSafe / Jev Pareto scoring (optional)

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

  Étiquettesreadme-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,

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

  Étiquettescall-site-verified

• arczhi/jet

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

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

  Étiquettesreadme-claim

• atharvamhaske/typesafe-sdk-go

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

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

  Étiquettesreadme-claim

• audreyt/paseo-spacedock

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

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

  Étiquettesreadme-claim

• automateyournetwork/netclaw

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

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

  Étiquettesreadme-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:

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

  Étiquettesreadme-claim

• awlevin/typesafe-computer-use

  README states:

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

  Étiquettescall-site-verified

• awslabs/agentcore-samples

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

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

  Étiquettesreadme-claim

• Ayush0054/metis

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

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

  Étiquettescall-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:

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

  Étiquettesreadme-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.*

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

  Étiquettesreadme-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.

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

  Étiquettesreadme-claim

• BeatAPI/awesome-jev

  README states:

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

  Étiquettescall-site-verified

• BenCaunt/jev-box-tracking

  README states: jev-box-tracking

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

  Étiquettesreadme-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

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

  Étiquettescall-site-verified

• Bewinxed/jevgpt

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

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

  Étiquettescall-site-verified

• bhaiG-de/jev-design-test

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

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

  Étiquettescall-site-verified

• BillionsBobby/JevRouter

  README states:

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

  Étiquettescall-site-verified

• bladedevoff/stuntd

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

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

  Étiquettesreadme-claim

• bodepudimuneendra-netizen/laya-jev-GraphRAG

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

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

  Étiquettescall-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.

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

  Étiquettescall-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).

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

  Étiquettescall-site-verified

• brandonbryant12/transcript-scorecard

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

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

  Étiquettescall-site-verified

• brnyxx/jev-ra

  README states:

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

  Étiquettescall-site-verified

• buberlo/jev-trader

  README states: jev-trader

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

  Étiquettesreadme-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。

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

  Étiquettesreadme-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.

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

  Étiquettescall-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.

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

  Étiquettesreadme-claim

• burnigtm/jev-mcp

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

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

  Étiquettescall-site-verified

• BYK/jev-mcp

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

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

  Étiquettescall-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

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

  Étiquettescall-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

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

  Étiquettescall-site-verified

• can1357/jegrep

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

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

  Étiquettesreadme-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)

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

  Étiquettescall-site-verified

• carldaws/hunch

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

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

  Étiquettesreadme-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

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

  Étiquettesreadme-claim

• cbruyndoncx/AskJev-MCP

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

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

  Étiquettescall-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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• CharlesFeng0314/JEV_sees

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

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

  Étiquettescall-site-verified

• Charlyhno-eng/jev-document-classification

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

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

  Étiquettesreadme-claim

• cheeaun/jevmoji

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

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

  Étiquettesreadme-claim

• CheshiAI/Cheshi

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

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

  Étiquettesreadme-claim

• chez-shanpu/typesafeai-go

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

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

  Étiquettescall-site-verified

• christos-antono/NPCTalk

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

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

  Étiquettesreadme-claim

• chy4pro/jev-for-chrome

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

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

  Étiquettesreadme-claim

• cobanov/awesome-jev

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

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

  Étiquettesreadme-claim

• cobusgreyling/Jev

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

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

  Étiquettesreadme-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).

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

  Étiquettescall-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.

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

  Étiquettesreadme-claim

• Cognipeer/agent-sdk

  README states: Against the real Jev API

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

  Étiquettesreadme-claim

• colliber/duckdb-jev

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

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

  Étiquettesreadme-claim

• columnar-tech/jevaro

  README states: A Python batching proxy for Jev that returns

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

  Étiquettesreadme-claim

• compozy/yoshi

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

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

  Étiquettesreadme-claim

• Contrastive-LM/CLM

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

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

  Étiquettescall-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:

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

  Étiquettescall-site-verified

• CTNicholas/jev-workflow-builder

  README states: Create an account on typesafe.ai

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

  Étiquettesreadme-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

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

  Étiquettesreadme-claim

• DanRWilloughby/snifftest

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

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

  Étiquettescall-site-verified

• danvega/jev-spring-boot-starter

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

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

  Étiquettesreadme-claim

• Das-rebel/a3m-router

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

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

  Étiquettesreadme-claim

• daseinlabs/open-jev

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

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

  Étiquettescall-site-verified

• davila7/jev-explained

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

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

  Étiquettescall-site-verified

• DECRUX9812/typesafe-skill-router

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

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

  Étiquettescall-site-verified

• delexw/claude-code-trace

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

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

  Étiquettescall-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) |

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

  Étiquettesreadme-claim

• devagrawal09/jev-review

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

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

  Étiquettescall-site-verified

• devagrawal09/stanley-code

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

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

  Étiquettesreadme-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。

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• devtooligan/jevscan-evm

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

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

  Étiquettesreadme-claim

• dfinke/Jev

  README states:

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

  Étiquettesreadme-claim

• Dicklesworthstone/skillranker

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

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

  Étiquettescall-site-verified

• Dimweaker/jev-libero

  README states:

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

  Étiquettescall-site-verified

• docxology/daf-jev

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

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

  Étiquettescall-site-verified

• doeixd/discern

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

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

  Étiquettesreadme-claim

• dominicrico/jev-router

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

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

  Étiquettesreadme-claim

• donvito/ai-backends

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

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

  Étiquettesreadme-claim

• dorkitude/webctl

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

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

  Étiquettesreadme-claim

• Dujaydis/JevSysUno

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

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

  Étiquettesreadme-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.

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

  Étiquettescall-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) |

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

  Étiquettesreadme-claim

• eriestra/browser-use-olympics

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

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

  Étiquettescall-site-verified

• Eriskii/ErisLint

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

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

  Étiquettescall-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

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

  Étiquettesreadme-claim

• etweisberg/jev-ui

  README states:

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

  Étiquettescall-site-verified

• EugeneBoondock/jevsql

  README states:

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

  Étiquettescall-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

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

  Étiquettescall-site-verified

• f-tiger/jev-decision-gate

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

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

  Étiquettescall-site-verified

• f/jev-leftpad

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

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

  Étiquettescall-site-verified

• fabricioctelles/skills

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

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

  Étiquettesreadme-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。

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

  Étiquettesreadme-claim

• featherless-ai/simple-jev

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

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

  Étiquettesreadme-claim

• feder-cr/jev

  README states:

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

  Étiquettescall-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.

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

  Étiquettescall-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。

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

  Étiquettescall-site-verified

• flitsinc/go-llms

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

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

  Étiquettesreadme-claim

• FluidInference/FluidUse

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

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

  Étiquettescall-site-verified

• Foadsf/jev-for-engineers

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

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

  Étiquettescall-site-verified

• FrancoisChastel/jev-code

  README states: jev-code

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

  Étiquettesreadme-claim

• freepik-company/jev-mcp

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

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

  Étiquettescall-site-verified

• frostney/clean-code-review

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

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

  Étiquettesreadme-claim

• gamesonrblx/Jevbridge

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

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

  Étiquettescall-site-verified

• gbh1234/Adaptive-rag

  README states: INTENT_BACKEND=jev

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

  Étiquettesreadme-claim

• genspark-ai/genoffice

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

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

  Étiquettescall-site-verified

• get-convex/convex-evals

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

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

  Étiquettesreadme-claim

• GhalebDweikat/winnow

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

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

  Étiquettescall-site-verified

• GhrezaKh74/JevTicktRouter

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

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

  Étiquettescall-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

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

  Étiquettesreadme-claim

• githubnext/localjev

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

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

  Étiquettescall-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

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

  Étiquettesreadme-claim

• GodsBoy/jev-agent-skill-router

  README states:

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

  Étiquettescall-site-verified

• gopaljigaur/decide

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

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

  Étiquettescall-site-verified

• Govcraft/emergent

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

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

  Étiquettesreadme-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

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

  Étiquettescall-site-verified

• GuSheng107/helpme-Jev

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

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

  Étiquettesreadme-claim

• hamgua/alpha-trading-bot-okx

  README states: Jev 快车道（TypeSafe System One）

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

  Étiquettesreadme-claim

• harlan-zw/harlan-agent-kit

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

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

  Étiquettesreadme-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.

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

  Étiquettescall-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.

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• hellozenstrategist-lab/eutrya

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

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

  Étiquettescall-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)

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

  Étiquettesreadme-claim

• hev/reranker

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

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

  Étiquettescall-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. |

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

  Étiquettesreadme-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。

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

  Étiquettesreadme-claim

• hotchpotch/jev-reranker

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

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

  Étiquettesreadme-claim

• hraness/algal

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

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• huntedman/JevLint

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

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

  Étiquettescall-site-verified

• HyunjunJeon/jev-judgment

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

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

  Étiquettesreadme-claim

• iamjonatha/decisionkit-dotnet

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

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

  Étiquettesreadme-claim

• iamtoomas/JevLint

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

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

  Étiquettescall-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 |

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

  Étiquettesreadme-claim

• iamvatsalpatel/tiershift

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

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

  Étiquettescall-site-verified

• iefnaf/pi-jev

  README states:

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

  Étiquettesreadme-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

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

  Étiquettesreadme-claim

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

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

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

  Étiquettesreadme-claim

• InternLM/Intern-Decision

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

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

  Étiquettesreadme-claim

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

  README states:

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

  Étiquettesreadme-claim

• ipenywis/laya-ultrafast

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

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

  Étiquettescall-site-verified

• ItIsCuthNotCup/MetaCog

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

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

  Étiquettesreadme-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.

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

  Étiquettesreadme-claim

• itsoltech/basal-rs

  README states:

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

  Étiquettesreadme-claim

• j1s4nn/duomind

  README states: Internet connection for setup and Jev API calls

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

  Étiquettesreadme-claim

• JamesANZ/us-legal-mcp

  README states: JEV_MODEL – default jev-latest

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

  Étiquettesreadme-claim

• jamesward/zio-typesafe-ai

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

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

  Étiquettescall-site-verified

• JanOstrowka/typesafe-assist

  README states:

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

  Étiquettescall-site-verified

• jaredpalmer/kev

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

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• jccrump/openbot

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

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

  Étiquettesreadme-claim

• jcpsimmons/jev-macos-loop

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

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

  Étiquettescall-site-verified

• JedimEmO/typesafe-client

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

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

  Étiquettescall-site-verified

• jerryfane/omp-jev-compaction

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

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

  Étiquettescall-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

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

  Étiquettesreadme-claim

• jhd3197/Prompture

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

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

  Étiquettescall-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

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

  Étiquettesreadme-claim

• jmanhype/jev-dspy-lab

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• jomatsu/pi-jev-auto-mode

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

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

  Étiquettescall-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

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

  Étiquettescall-site-verified

• jonathanavis96/jev-kit

  README states: What is Jev, and why a kit

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

  Étiquettesreadme-claim

• jozefRudy/job_search

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

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

  Étiquettesreadme-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.

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

  Étiquettesreadme-claim

• jujumilk3/jev-calibration-audit

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• jxucoder/mimicry

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

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• keltokhy/jgrep

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

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

  Étiquettesreadme-claim

• kesku/jev-freeform

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

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

  Étiquettescall-site-verified

• kevinbadi/jev-voice

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

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

  Étiquettescall-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.

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

  Étiquettesreadme-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.

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

  Étiquettesreadme-claim

• KiritoKing/midscene-jev-runner

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

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

  Étiquettesreadme-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.

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

  Étiquettescall-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.

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• kouhxp/gutsy

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

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

  Étiquettescall-site-verified

• kraayenjon/awesome-jev

  README states:

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

  Étiquettesreadme-claim

• kshetrajna12/reflex

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

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

  Étiquettescall-site-verified

• kyegomez/open-jev

  README states: System One Models and Jev

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

  Étiquettesreadme-claim

• kyu1204/jgrep

  README states: jgrep runs on Jev, through TypeSafe or

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• lakeday-org/perch

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

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

  Étiquettescall-site-verified

• lhotwll217/jev-cli

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

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

  Étiquettescall-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.

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

  Étiquettesreadme-claim

• libingzheren/Jev-Mem

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

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

  Étiquettescall-site-verified

• liu-x27/XavierJev

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

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

  Étiquettescall-site-verified

• liuyanghejerry/Clausura

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

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

  Étiquettesreadme-claim

• luisleo526/doc2mark

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

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

  Étiquettesreadme-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.

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

  Étiquettescall-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

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

  Étiquettesreadme-claim

• maayanlevy/mysql-ailike

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• MahmoudAdelbghany/jev-browser

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

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

  Étiquettescall-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

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

  Étiquettescall-site-verified

• maker-KK/todo-jev

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

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

  Étiquettescall-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.

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

  Étiquettesreadme-claim

• mandu5/jevcompat

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

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

  Étiquettesreadme-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。

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

  Étiquettescall-site-verified

• marcreichel/laya-php

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

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

  Étiquettescall-site-verified

• MarissaFamularo/citation-verifier

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

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

  Étiquettesreadme-claim

• markjaquith/typesafe-ai-playground

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• mattn/go-jev

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

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

  Étiquettescall-site-verified

• mejiasd3v/pi-jev-router

  README states:

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

  Étiquettescall-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。

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

  Étiquettesreadme-claim

• Micha0827/snapjudge

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

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

  Étiquettesreadme-claim

• misbahsy/doc-router

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

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

  Étiquettesreadme-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).

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

  Étiquettesreadme-claim

• mizchi/jev-lint

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

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

  Étiquettescall-site-verified

• mizchi/jev-test-filter

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• mmastrac/djev

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

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

  Étiquettescall-site-verified

• mmastrac/djev-spark

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

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

  Étiquettescall-site-verified

• mohsen1/llm-debugger-vscode-extension

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

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

  Étiquettesreadme-claim

• morganlinton/Albatross

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

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

  Étiquettescall-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

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

  Étiquettescall-site-verified

• mossyfield/ST-jeved

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

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

  Étiquettescall-site-verified

• mrbanana55/Decision_Blackjack

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

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

  Étiquettesreadme-claim

• mrmps/classifier-dev

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

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

  Étiquettesreadme-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

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

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

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

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

  Étiquettesreadme-claim

• NandhaKishorM/laya

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

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

  Étiquettescall-site-verified

• Nasrallah-AL/jev-cli

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

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

  Étiquettesreadme-claim

• nassim-arifette/jevgrep

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

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

  Étiquettescall-site-verified

• ndolinschi/harnessjudge

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

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

  Étiquettescall-site-verified

• ndolinschi/pulselane

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• newfull5/malkuth

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

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

  Étiquettescall-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.

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

  Étiquettescall-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.

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

  Étiquettescall-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:

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

  Étiquettesreadme-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)

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

  Étiquettescall-site-verified

• nidhi-singh02/agent-router

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

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

  Étiquettescall-site-verified

• Nisaka520/JevIntent

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

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

  Étiquettesreadme-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.

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

  Étiquettescall-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.

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• notque/vexjoy-agent

  README states: /d — Jev-Powered Router

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• Nyarlathoteppppp/pi-heed

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

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

  Étiquettescall-site-verified

• obie/ruby_decision_model

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

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

  Étiquettesreadme-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

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

  Étiquettesreadme-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.

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

  Étiquettescall-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.

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

  Étiquettescall-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

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

  Étiquettesreadme-claim

• OmniJev/OneJev

  README states:

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

  Étiquettescall-site-verified

• ondata/vd-jev

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

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

  Étiquettesreadme-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:

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

  Étiquettescall-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:

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• OskarLebuda/precog

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

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

  Étiquettesreadme-claim

• oso95/x-scanner

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

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• pavy23/web-doom

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

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

  Étiquettesreadme-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。

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

  Étiquettesreadme-claim

• PerryLink/jevcore

  README states: TypeSafe Jev for DeepSeek Harness

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

  Étiquettesreadme-claim

• peterfriese/system-one-foundation-models

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

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

  Étiquettesreadme-claim

• philippdubach/pi-jev-router

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

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

  Étiquettescall-site-verified

• picaye/jev-compaction

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

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

  Étiquettesreadme-claim

• PistachioAIHQ/jev-synergy-screening

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

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

  Étiquettescall-site-verified

• pithings/advocaat

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

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

  Étiquettescall-site-verified

• PixelML/av

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

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

  Étiquettesreadme-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

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

  Étiquettesreadme-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

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

  Étiquettescall-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,

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

  Étiquettesreadme-claim

• PyModel/jev-judge-mcp

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

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

  Étiquettescall-site-verified

• qddegtya/qualm

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

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

  Étiquettesreadme-claim

• qkal/Canny

  README states: Jev

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

  Étiquettesreadme-claim

• QuentinDanblon/pi-fast-jev-compaction

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

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

  Étiquettescall-site-verified

• Query-farm/vgi-typesafe

  README states:

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

  Étiquettescall-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.

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

  Étiquettesreadme-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

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

  Étiquettesreadme-claim

• rajivkuriakose/typesafe-jev-examples

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• RayenMlayeh/jevcrawl

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

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

  Étiquettesreadme-claim

• rbalch/typesafeai-review

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

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

  Étiquettesreadme-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).

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

  Étiquettescall-site-verified

• reachjalil/jevlogs

  README states:

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

  Étiquettesreadme-claim

• ReallyArtificial/stuntdouble

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

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

  Étiquettescall-site-verified

• realZachi/pg-jev

  README states:

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

  Étiquettesreadme-claim

• realZachi/typesafe-adblock

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

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

  Étiquettescall-site-verified

• receptron/laya

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

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

  Étiquettesreadme-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.

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• rohanarun/computer-use-cache

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

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

  Étiquettescall-site-verified

• rokbenko/quackd

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

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

  Étiquettescall-site-verified

• RomanSlack/jev-drone

  README states: jev-drone

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

  Étiquettesreadme-claim

• romeromarcelo/jev-retrieval

  README states:

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

  Étiquettescall-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

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

  Étiquettesreadme-claim

• runta-dev/jot

  README states: 

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• ryana/jevify

  README states: TypeSafe introduction

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• samdotmak/jev-recall

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

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

  Étiquettescall-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?*

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• savka777/jev-use

  README states:

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

  Étiquettescall-site-verified

• schwarzschlyle/immune

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

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

  Étiquettescall-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

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

  Étiquettesreadme-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.

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

  Étiquettesreadme-claim

• SeeAPI/awesome-jev-use-cases

  README states:

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

  Étiquettescall-site-verified

• sgzmd/rss-morning

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

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

  Étiquettesreadme-claim

• shaharia-lab/jev-cli

  README states:

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

  Étiquettescall-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.

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• shantanugoel/mario-jev

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

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

  Étiquettescall-site-verified

• sharziki/semdecide

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

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

  Étiquettescall-site-verified

• shhivv/arc-cua

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

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

  Étiquettescall-site-verified

• shinshin86/aituber-onair

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

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

  Étiquettesreadme-claim

• shitianfang/jev-use

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

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

  Étiquettesreadme-claim

• shivendrasoni/vector-cache

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

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

  Étiquettesreadme-claim

• ShuhanSun/jev-oas-sentinel

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

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

  Étiquettescall-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.

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

  Étiquettesreadme-claim

• socai-io/jev-social

  README states:

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

  Étiquettescall-site-verified

• sonnylazuardi/superterminal

  README states: The ranking comes from Jev,

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

  Étiquettesreadme-claim

• sorrycc/typesafe-snake

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• SoundBlaster/Jev4Mellea

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

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

  Étiquettescall-site-verified

• SREGym/SREGym

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

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

  Étiquettescall-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.

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

  Étiquettescall-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.

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• STRML/omp-jevens-classifier

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

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

  Étiquettescall-site-verified

• sufianetaouil/every

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

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

  Étiquettescall-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.

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

  Étiquettescall-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

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

  Étiquettesreadme-claim

• supercorp-ai/supercov

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• tacticocc/Jevbridge

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

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

  Étiquettescall-site-verified

• tamnd/kime

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

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

  Étiquettesreadme-claim

• tanghaojin/x-smart-tags

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

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

  Étiquettesreadme-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.

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

  Étiquettesreadme-claim

• TauricResearch/TradingAgents

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

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

  Étiquettescall-site-verified

• tbdavid2019/ai-hedge-fund-API

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

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

  Étiquettesreadme-claim

• The-Vibe-Company/quivr

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

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

  Étiquettesreadme-claim

• TholeG/typesafe-chess

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

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

  Étiquettesreadme-claim

• TianyuCodings/JevHarness

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

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

  Étiquettesreadme-claim

• timpratim/macbrow

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

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

  Étiquettesreadme-claim

• tinyhumansai/opencompany

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

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

  Étiquettesreadme-claim

• TKY-27/JevSlop

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

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

  Étiquettescall-site-verified

• togethercomputer/tev1

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

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

  Étiquettesreadme-claim

• TokenTrim/jev-routing-experiment

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

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

  Étiquettescall-site-verified

• tonone-ai/tonone

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

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

  Étiquettesreadme-claim

• tonsky/tgadmin

  README states: With Jev

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

  Étiquettesreadme-claim

• tpaulshippy/shady-town

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

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

  Étiquettesreadme-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. |

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

  Étiquettesreadme-claim

• trpc-group/trpc-agent-go

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

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

  Étiquettesreadme-claim

• truespar/sentio

  README states: provider = "jev"

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

  Étiquettesreadme-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

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• tylergibbs1/sift

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

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

  Étiquettescall-site-verified

• tylerjharden/ailerix

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

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

  Étiquettescall-site-verified

• typakon4/jev-layer

  README states:

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

  Étiquettescall-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

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

  Étiquettesreadme-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.

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

  Étiquettescall-site-verified

• UditAkhourii/quicksilver

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

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

  Étiquettesreadme-claim

• uehaj/sys1grep

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

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

  Étiquettesreadme-claim

• uezo/aiavatarkit

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

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

  Étiquettescall-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.

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

  Étiquettesreadme-claim

• uu889/laya-opencv

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

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

  Étiquettesreadme-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.

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

  Étiquettesreadme-claim

• valentynkit/awesome-jev-typesafe

  README states:

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

  Étiquettescall-site-verified

• valentynkit/jev-commit

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

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

  Étiquettescall-site-verified

• valentynkit/jev-skip

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

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

  Étiquettesreadme-claim

• vinilana/live-jev

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

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

  Étiquettesreadme-claim

• vnmoorthy/siege

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

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

  Étiquettesreadme-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

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

  Étiquettescall-site-verified

• walidboulanouar/awesome-jev-use-cases

  README states:

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

  Étiquettesreadme-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 |

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

  Étiquettesreadme-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.

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• whyashthakker/awesome-jev-use-cases

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

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

  Étiquettescall-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.

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

  Étiquettescall-site-verified

• wobsoriano/is-jeven

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

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

  Étiquettescall-site-verified

• wustep/jev-playground

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

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

  Étiquettescall-site-verified

• Xiaooolong/vev

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

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

  Étiquettesreadme-claim

• xinyao27/jevonian

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

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

  Étiquettescall-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 |

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

  Étiquettesreadme-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

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

  Étiquettesreadme-claim

• yairshy/decido

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

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

  Étiquettescall-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「

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

  Étiquettesreadme-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

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

  Étiquettesreadme-claim

• Yinsongxu/LLM2Jev

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

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

  Étiquettescall-site-verified

• ZeroGold/call-coach-ai

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

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

  Étiquettescall-site-verified

• ZeroTang05/VideoAdGuard

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

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

  Étiquettesreadme-claim

• zhengxuyu/litjev

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

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

  Étiquettescall-site-verified

• zhuyansen/jev-search-rerank-eval

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

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

  Étiquettesreadme-claim

• zsavage8/padflow-jev-evals

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

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

  Étiquettescall-site-verified