- 151system-oneProvider-neutral System One runtime for TypeScript and Pi
iamaamir/system-one · TypeScript
756calibrated-classificationchoice-noul-scoredecision-modelmodel-routingpi-coding-agentprovider-neutralreflex - Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks
ikermoel/open-alternative-jev · Python
7414calibrationclassificationjev-alternativellmlogprobsopen-jevopen-source-jev - 153stuntdLocal proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.
bladedevoff/stuntd · Python
745claude-codedistillationlayallmllm-proxylocal-inferenceopenai-compatible - 154pi-jevSemantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev
TheoOliveira/pi-jev · TypeScript
7214typescriptpi-coding-agentpi-extensionpi-package - 155awesome-jevA source-reviewed gallery of JEV-related projects with 50+ GitHub stars — integrations, tools, open models, experiments, and ecosystem resources. Live gallery: beatapi.io/awesome-jev
BeatAPI/awesome-jev · JavaScript
719ai-agentsawesome-listdecision-modeljavascript - 156JevstillerDistill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.
tomerglick57/Jevstiller · Python
7111classificationdistillationknowledge-distillationllmmlopsmodel-cascadepython - 157JevIntent微信（FkWeChat 插件）：长按消息分析意图 / 情绪 / 回复姿态，只在本机弹提示，对方无感知
Nisaka520/JevIntent · Java
709androidchat-analysisfkwechatintent-recognitionlsposedplugin - 158OpenJevOpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisions and browser-agent steps.
alanhuangyoo/OpenJev · Python
704browser-agentdecision-modeldistillationjev-alternativellmlocal-llmopenjev - OpenThai-SystemOne: open Thai + English System One decision model (0.8B, 256-way slot head, Apache-2.0)
iapp-technology/openthai-systemone · Python
6923python - 160typesafe.protypesafe.pro: TypeSafe Jev ecosystem repository.
chigwell/typesafe.pro · Python
670python - 161jev-mcpMCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client
burnigtm/jev-mcp · TypeScript
6611typescript - 162jev-rulesJev picks which of your rules apply to each prompt, so Claude only sees the ones that matter.
EliaAlberti/jev-rules · JavaScript
6612javascript - 163jeviewAn unofficial local visualizer for Jev (TypeSafe): a live view of every call your code makes. Not affiliated with TypeSafe AI.
andududu/jeview · JavaScript
6611ai-agentsdebuggingdeveloper-toolsllm - 164jev-useClaude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM
shitianfang/jev-use · JavaScript
6514ai-agentsagent-skillsclaude-codeclaude-code-hooksclaude-code-pluginclaude-skills - 165jev-ui-testJev 决策模型驱动的 UI 自动化测试框架：不生成「下一步做什么」的文字，而是在候选元素里直接打分；一句话写用例，pytest 执行，Allure 出报告，每个操作决策中位 458 ms（UI test automation driven by the Jev decision model — scored decisions, not generated prose; ~458 ms per decision）
buer2233/jev-ui-test · Python
6413ai-testingallure-reporte2e-testingjev-ui-testjev-ultrafastpytestpython - 166RoboJEVTwo-stage JEV control of a Franka Panda in MuJoCo
lykycy123/RoboJEV · Python
643python - 167jev-designCan a model design a dashboard? A console whose whole design system is generated at runtime by Jev from a one-sentence brief.
bilune/jev-design · TypeScript
624typescript - 168jgrepgrep for what code does, not what it's called. Semantic code search powered by TypeSafe Jev.
kyu1204/jgrep · TypeScript
625typescript - A Java SDK for the TypeSafe AI JEV API, & Spring AI TypeSafe integrations.
spring-ai-community/spring-ai-typesafe · Java
6218java - 170grevThinking coreutils
aurorainfra/grev · Go
611coreutilsgo - Ruby client for decision models such as Typesafe Jev
obie/ruby_decision_model · Ruby
596ruby - 172laya-opencvOpenCV 与判定模型（Laya / Jev）结合的本地工作台：OpenCV 看图测量，硬规则管数字，模型下结论。用于水果采摘、杂草与害虫监测、钢管和纺织物质检。 | OpenCV + Laya/Jev decision models in a one-click local workbench: OpenCV measures, hard rules settle the numbers, the model gives the verdict. For agriculture and quality inspection.
uu889/laya-opencv · Python
588python - 173levAn open System One decision model
Abhinavexists/lev · Python
583modalqwenpython - 174jev-codeJev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command setup.
FrancoisChastel/jev-code · TypeScript
557agent-skillsclassifierclaude-codecodexcoding-agentsmcpopencode - A database-agnostic Agentic GraphRAG framework using swappable System One models (local Laya / cloud Jev). A plug-and-play intelligence layer featuring a complete 4-phase pipeline, continuous evaluation and custom A* traversal for any graph database.
bodepudimuneendra-netizen/laya-jev-GraphRAG · Python
533astar-algorithmeval-harnessfine-tuninggraphdatabasegrapraglayaneo4j - Route HTTP requests by meaning. A semantic router for Hono powered by Jev.
yusukebe/hono-jev-router · TypeScript
524typescript - 177hermes-nerveNerve is a supervisory nervous system for Hermes agents, adding typed System One decisions, ranking, verification, token-aware oversight, and an opt-in tool gate powered by TypeSafe Jev or Open Source Laya
keeltrace/hermes-nerve · Python
5116python - 178jevreelA zero-embedding approach to video intelligence, using Jev: contact sheets + typed decisions, as MCP tools and a skill for any coding agent.
DeepAleph/jevreel · Python
515agent-skillsclaude-codecontact-sheetsdecision-modelmcpvideovideo-search - The highly anticipated open-source repository for JEV as Policy enables one-click setup of the simulation environment. Evaluations of Astra + JEV on benchmarks such as RoboTwin will also be released soon.
YuanKJing/Jev-as-Policy · Python
503python - Jev-Moderation-Bot: TypeSafe Jev ecosystem repository.
brainstormity/Jev-Moderation-Bot · Python
506python - 181jev-siftClassify first. Read selectively. A portable agent plugin and MCP tool for batch text classification.
kbhuw/jev-sift · JavaScript
503javascript - 182vibecheckChrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post
RafalWilinski/vibecheck · JavaScript
504javascript - Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
PyModel/jev-judge-mcp · Python
495agent-toolsai-agentsai-guardrailsclassificationclaude-codefact-checkingguardrails - Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.
intikhab49/open-jev-typed-decision-engine · Python
494agent-observabilitycalibrationcolabdecision-modelexpected-calibration-errorhuggingfacellm-alternative - 185pi-typesafeTypeSafe decisions for Pi: batched evaluation tool, terminal playground, and typed API for extension authors
DevMortimer/pi-typesafe · TypeScript
4814typescript - 186JevbridgeACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
tacticocc/Jevbridge · TypeScript
474acpai-agentsclaudecomputer-usegrokllmopencode - 187jevifyAn agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.
altryne/jevify · Python
473agent-skillsai-agentsthursdaipython - 188litjevTurn any off-the-shelf LLM into a Jev -like decision layer
zhengxuyu/litjev · Python
4710python - A Swift package for typed decisions from language models (probabilities, choices, and scores), with support for local MLX models and the TypeSafe Jev API.
mattt/AnyDecisionModel · Swift
464mlx-lmswift
第 151–200 条，共 3056 条