A free GitHub project directory for the TypeSafe Jev / System One model.Explore official SDKs, agent tools, open-source alternatives and Jev news.

Data updated

  • High-throughput, robust native DuckDB extension for batched and streaming TypeSafe/Jev classification, scoring, and semantic predicates from SQL.

    prasanthj/duckdb-jev · C++

    153
    classificationc++data-engineeringduckdbduckdb-extensionllm
  • A browser extension that lights up the paragraph that answers your question

    tymscar/hunch · TypeScript

    156
    typescript
  • 353jev
    An unofficial, provider-neutral Unix client for Jev from TypeSafe AI. Written in Go.

    stefafafan/jev · Go

    151
    cligo
  • Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).

    1arley/jev-advisor-gateway · TypeScript

    151
    anthropicclaude-codecodexdevingatewaygeminikilo
  • Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives.

    TarunTomar122/jev-askable-arm · Python

    152
    python
  • Jev-assisted retrieval and evidence-preserving inspection for local Markdown, Obsidian vaults, and Logseq Markdown graphs.

    Emlembow/jev-graph-search · JavaScript

    153
    logseqmarkdownobsidianjavascript
  • Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.

    AntonioCoppe/jev-harness · TypeScript

    152
    ai-agentsconfidencedecisionevaluationharnessllm
  • jev-me is grill-me with jev

    jon-devlapaz/jev-me

    152
    python
  • Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM

    prismhq/jev-router · Python

    151
    python
  • A stronger one-pass scorer over a variable list of text options. Hashed n-gram encoder, rival-aware attention, gated head, temperature scaling — with a head-to-head benchmark vs the jevlike starter design.

    olanotolu/jevbetter · Python

    153
    python
  • Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

    iamtoomas/JevLint · TypeScript

    150
    typescript
  • psql-shaped CLI and Go/TypeScript/Python SDKs that add jev(), jev_prob, jev_choice, and jev_score to queries against vanilla Postgres with no extension: plain SQL runs on the server, surviving rows are judged by Jev in batches, and the client applies the filter, sort, or group.

    kylemclaren/jevql · Go

    151
    postgressqlclisdk
  • knowlery: TypeSafe Jev ecosystem repository.

    JayJiangCT/knowlery · TypeScript

    151
    typescript
  • Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter

    jerryfane/omp-jev-compaction · TypeScript

    152
    routercompaction
  • openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド

    genai-craft/openvons · Python

    150
    pythoncalibrationdecision-modeljapanese
  • Typed TypeSafe AI clients for Rust, with async and blocking backends and observable retries.

    Twister915/typesafe-ai · Rust

    154
    rust
  • Interactive experiments with TypeSafe Jev, from support routing to 3D driving simulations with real AI decisions and visible sensor inputs.

    kavehmz/typesafe-playground · JavaScript

    154
    javascript
  • TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.

    DECRUX9812/typesafe-skill-router · Python

    157
    pythonai-agentshermes-agenthermes-plugin
  • 是非选择问Jev

    kuhung/ask-jev · TypeScript

    142
    typescript
  • Question patterns, anti-patterns & calibration notes for Jev (TypeSafe AI) — the prompt engineering of typed decisions. 43 entries, 8 categories. EN/中文.

    vicfei/awesome-jev-prompts · Python

    141
    awesomeawesome-listdecision-modelllmprompt-engineeringstructured-output
  • 🌳 Groot 1 — open typed-decision model. Calibrated choice/score/yes-no answers over 64k-token states, System One API compatible, with a pure Bend engine. Beats Jev on zero-shot Folha news (87.8% vs 85.8%) and typed decisions (75.3% vs 73.7%).

    leofmarciano/groot · Python

    143
    bendbend-langcalibrationdecision-modelllm-routinglong-contextmachine-learning
  • opencode plugin: a System One decision model judges every bash command before it runs — destructive / credentials / your guardrails.md policy

    berget-ai/guardrails-md · TypeScript

    143
    ai-safetyguardrailsopencodeopencode-plugintypescript
  • Eyes are All JEV Needs - real time visual devisions from RGB, video and RGB-D cameras.

    CharlesFeng0314/JEV_sees · Python

    140
    computer-visionmultimodal-aiobject-detectionobject-trackingpythonreal-time-airgbd
  • Memory-backed job-application skill: Jev selects, an LLM writes only new text, Playwright fills. Greenhouse + Ashby.

    TheAdaply/jev-apply · JavaScript

    144
    javascript
  • Chrome extension that cleans up your LinkedIn feed: hides engagement bait, self-promo and off-topic posts using Jev, TypeSafe AI's typed classification model — and explains every decision.

    stefw/lkclean · TypeScript

    142
    browser-extensionchrome-extensioncontent-classificationfeed-filterlinkedinlinkedin-feed
  • Route pi prompts to task-appropriate model tiers with TypeSafe Jev typed judgments. Budget-aware, with automatic fallback.

    da-vinci-noob/pi-jev-model-router · TypeScript

    149
    typescript
  • Typed, calibrated decisions from a local model. No text generated.

    bradAGI/ruling · Python

    142
    python
  • Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text generation. TypeSafe-compatible HTTP API, runs on MLX.

    Micha0827/snapjudge · Python

    140
    apple-siliconclassificationdecision-makingfastapillmllm-evaluationlocal-llm
  • A small, extensible decision-to-action harness for TypeSafe Jev

    Kevthetech143/super-jev · Python

    142
    typescript
  • A decision model that returns calibrated answers to yes/no, choice, score and multi-label questions.

    SamratDuttaOfficial/WaterSheep · Python

    144
    browsercalibrationdecision-modelhuggingfacejavascriptjev-alternativelocal-first
  • Jev judgment, not generation: prune long tool output, screen fetched pages for injected instructions, and gate completion claims inside DeepSeek Harness.

    HorusJiang/dsh-jev-tools · TypeScript

    132
    context-windowdeepseek-harnessdshdsh-pluginllmprompt-injection
  • Probabilistic control flow for Ruby and Rails - powered by TypeSafe's Jev

    carldaws/hunch · Ruby

    130
    rubyruby-gems1-models
  • One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.

    tontoko/jev-browser · JavaScript

    132
    javascriptbrowser-automationclimcp
  • Filter any live Twitch chat with Jev: a bring-your-own-key Chrome extension

    ethanplusai/jev-chat-for-twitch · JavaScript

    132
    javascript
  • DataFusion SQL functions for typed judgments. TypeSafe is one server.

    parable-work/jev-datafusion · Rust

    131
    rust
  • 📏 Claude Code plugin that makes Claude follow your AGENTS.md: every reply and edit checked by TypeSafe Jev ✅

    erkamyaman/jev-enforce · TypeScript

    132
    claudeclaude-codeclaude-code-pluginclaude-mdcode-qualitydeveloper-tools
  • Jev vs DeepSeek 医疗任务对比:12 类场景、96 项测试,效果、耗时与费用一览。 | Jev vs DeepSeek on 96 healthcare tasks across 12 scenarios: quality, latency, cost and open experiment data.

    JuneYaooo/jev-healthcare-lab · Python

    131
    benchmarkchinese-nlpclinical-nlpclinical-trialsdatasetsdeepseekevidence-based-medicine
  • LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.

    rajdhakad9826/jev-router · TypeScript

    131
    typescript
  • Jev + A2UI = ?

    dglazkov/jev2ui · TypeScript

    132
    typescript

351–400 of 3054