Launches on September 20, 2026
Repositories created on this date, ranked by GitHub stars. They launched the same day, so their stars compare directly.
- 2510
Fast browser hands for coding agents: name an outcome, and Jev (TypeSafe's decision model) picks each click in about 300 ms. MCP server, Claude Code plugin, library and CLI; works in a browser it launches or in your own Chrome or Edge.
- 2520
Ten things you need approved, and a reviewer you have to convince. Every verdict is a typed judgement rule answered by jev, a pinned TypeSafe System One model — a probability, not a sentence.
- 2530
A cinematic 2D rescue game powered by TypeSafe Jev. Six people, 35 seconds, and live AI decisions under pressure.
- 2540
Bezel is a harness agnostic supplemental overlay. Jev integration, bend2 planned. current status prototype, will be written in Rust after PoC
- 2550
AI 恰饭跳过:用 Jev (TypeSafe) 从字幕里找出 B 站视频的恰饭段落并自动跳过的 Chrome 插件(youtube-sponsor-detection 的 B 站移植)
- 2560
Chrome extension that sorts your X bookmarks into folders with a little help from TypeSafe’s Jev.
- 2570
macOS 命令行工具:把一句中文指令变成受控的应用操作,每一步执行完都由代码回读验证
- 2580
Low-memory autonomous web classification with HTTPX, Lightpanda and Jev
- 2590
Interactive smart home demo comparing local Laya (MLX) with Jev (TypeSafe API) using shared routing and safety rules.
- 2600
♠️ 76 questions for the AI that can't refuse — Jev (TypeSafe) answers everything, live. Guess its verdict.
- 2610
Puntuar currículums de ciberseguridad con JEV, el modelo System One de TypeSafe, sobre Cloudflare Workers. Clasificación contra NICE, ECSF y SFIA, con cada número trazable hasta la pregunta que lo produjo.
- 2620
Local chess study tool: Stockfish 19 WASM for search, TypeSafe AI's Jev as a no-search intuition layer
- 2630
A pygame chess game with Jev as the AI opponent. Play Human vs Human, Human vs Jev, or watch Jev vs Jev.
- 2640
Use a local classifier engine through the typesafe.ai Jev API schema — FastAPI drop-in proxy.
- 2650
Local typed decisions with rules, Laya, DistilBERT, and Qwen backends, plus deterministic Hermes and artifact guards.
- 2660
Reduza tokens de entrada no Claude Code com compactação de contexto por relevância (LiteLLM + TypeSafe Jev). Tutorial bilíngue PT-BR / EN.
- 2670
Coffee Under Fire: a free browser shooter with NPC tactics powered by TypeSafe AI’s Jev model. Play at https://coffee.yardsort.sh/
- 2680
Make decisions from the command line, in scripts, and in agent skills. No code required.
- 2690
The judgment API — TypeSafe Jev (System One) on Cloudflare Workers. Classify text into triage/urgency/spam/tone/risk with calibrated confidence, agent-discoverable. Judgment proposals only.
- 2700
Versioned Jev decision contracts with typed validation, deterministic policies and historical replay.
- 2710
Reproducible quantitative research CLI for testing momentum strategies and auditing research methodology with TypeSafe Jev.
- 2720
DeepSeek Harness (DSH) 执行前安全阀门:bash/pwsh 真正执行前先经静态规则 + TypeSafe Jev 语义判定,破坏性操作按 允许/修正/拦截/上报人工 四态处置,含额度降级与审计日志。
- 2730
Memory plugin for DeepSeek Harness: every memory read/write is a typed judgement by TypeSafe Jev (choice/noul).
- 2740
TypeSafe Jev (System One) as DeepSeek Harness agent tools, with the token accounting and benchmark to prove what they cost
- 2750
Chromium MV3 extension: watches a DXS market and asks Jev (TypeSafe) for a signal-only buy/hold/sell read. Never trades.
- 2760
Reproducible F1 forecasting harness comparing TypeSafe Jev with OpenAI models on identical pre-race evidence
- 2770
FOMC hawkishness: TypeSafe Jev pairwise Choice vs rate actions (+ Haiku 4.5 comparison). Pages in /docs.
- 2780
Plugin WordPress: trova i link interni che mancano e gli articoli doppi. Propone, non scrive. Giudizi di Jev (TypeSafe AI).
- 2790
FizzBuzz powered by Jev, TypeSafe AI's System One model.
- 2800
Flappy Bird played by TypeSafe's Jev: one yes/no question per frame, no text generation. Cloudflare Worker.
- 2810
Testing flappy bird with SystemOne Jev like model locally
- 2820
Local open-source drop-in for TypeSafe AI Jev + Universal WebMCP Chrome Extension — Noul/Choice/Score at 10-50ms with Transformers.js
- 2830
A focused Chromium extension that uses JEV to keep browsing aligned with one session goal.
- 2840
経営管理(FP&A)を TypeSafe Jev で実装するデモ。取込データ→マスタ項目の意味的マッチングと、PL表のセマンティックハイライト
- 2850
G1 DE IDEIAS — globo.com de ideias com JEV + OCR (Fábio Rosestolato). Portal estático 24/7: Tesseract + TypeSafe JEV 300ms + Flask + Vercel/Cloudflare.
- 2860
Public Gentle Shell fork exploring an optional TypeSafe/JEV context-anticipation integration
- 2870
Jev decides, Grok Bot executes, humans control irreversible actions. A decision router for Grok Bot built on TypeSafe AI's Jev.
- 2880
Jev (TypeSafe AI) evaluation plugin for Hermes Agent — structured decision/classification/routing tool via Vercel AI Gateway
- 2890
Unified Hermes Agent + Desktop plugin: TypeSafe Jev routes misspelled, shortened, and meaning-based slash commands to real ones. Advisory memory, fresh Jev decision every time.
- 2900
Documentation hub for Hermes Agent + Jev (TypeSafe System One Model) integration
- 2910
tiny Jev-like model. Jev and Kev inspired.
- 2920
Sentence heatmaps and paragraph main ideas, scored by TypeSafe's Jev model. Bring your own API key.
- 2930
How good is Jev? TypeSafe Jev vs an LLM on the same intent-routing task.
- 2940
Infra guardian to protect downstream resources and gracefully handle system degradation at scale
- 2950
Turn Jev judgments into versioned business events with uncertainty, durable state and an outbox.
- 2960
An npm CLI that audits a codebase against ISO/IEC 27001:2022 Annex A and writes a detailed `iso-jevdit-report.md` you can hand to an auditor.
- 2970
Jasper's Trade Bot — Kalshi 15-minute BTC YES/NO desk (no secrets)
- 2980
Send typed questions to TypeSafe System One and receive typed Ruby response objects.
- 2990
Independent, pre-registered evaluation of TypeSafe AI's Jev. 5,721 calls, 21 experiments, 50 predictions registered before collection. Raw data included.
- 3000
Haskell library for using TypeSafe AI's Jev