Awesome Jev
Projects built on Jev, curated by Jev. Every repository below was collected from GitHub and judged by Jev in a single call. Code applies the policy; nothing was hand-picked. How it works.
jaredpalmer/kev
★ 9.8kgithub ↗Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
genuine0.94cat0.97subst2.94Research and EvalsPythonreadme pickTurn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
genuine0.65cat0.74subst2.95Research and EvalsPythonreadme pickJev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
genuine0.91cat0.99subst2.86Agent and Dev ToolingPythonreadme pickrealZachi/pg-jev
★ 1.2kgithub ↗Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.
genuine0.97cat1.00subst2.93IntegrationsShellreadme pickMapika/decider
★ 1.2kgithub ↗A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.
genuine0.88cat1.00subst2.91Research and EvalsPythonreadme pickJevBench by Benchmark Heaven: benchmark and leaderboard for AI decision models, measuring typed decision accuracy, calibration, latency and cost.
genuine0.93cat1.00subst2.99Research and EvalsPythonreadme pickTyped-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.
genuine0.95cat0.91subst2.98Research and EvalsHTMLreadme pickNo description provided.
genuine0.65cat0.77subst2.94Research and EvalsPythonreadme pickTurn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.
genuine0.88cat0.65subst2.99IntegrationsPythonreadme pickReflexBench — open benchmark and evaluation harness for System One models and typed decision engines
genuine0.87cat1.00subst2.97Research and EvalsPythonreadme pickfeder-cr/jev
★ 1.4kgithub ↗jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.
genuine0.94cat0.92subst2.97Research and EvalsC++readme pickClaude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything else
genuine0.95cat0.99subst2.85Agent and Dev ToolingJavaScriptreadme pickA measured tool-call firewall for AI agents: allow, ask or deny before the agent acts. Claude Code mod and hook, MCP proxy. Built on TypeSafe Jev, measured on real sessions with a blind second labeler.
genuine0.89cat0.97subst2.94Agent and Dev ToolingTypeScriptreadme pickOpen-source, local decision models inspired by TypeSafe’s Jev and System One - built on Qwen3 for NVIDIA DGX Spark.
genuine0.84cat1.00subst2.90Research and EvalsPythonreadme pickOpen decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
genuine0.62cat0.54subst2.96Research and EvalsPythonreadme pickBrowser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
genuine0.99cat0.50subst2.89Agent and Dev ToolingJavaScriptreadme pickAI-powered Python library that converts any document (PDF, Word, Excel, PowerPoint, HTML) to clean Markdown while preserving complex tables and layouts using AI-Powered OCR technology.
genuine0.82cat0.28subst2.95Applications?Pythonreadme pick弦外之音 —— 微信聊天里的关系进展助手:读屏(无障碍树 / 截屏视觉)→ Jev 判读 + 攻略度 → 聊天模型出 3 条候选回复,攻略度常驻挂在屏幕上。不改微信、不发消息、不注入点击。
genuine0.97cat1.00subst2.93ApplicationsKotlinreadme pickSuper fast Jev like server, model agnostic, working with any OpenAI compatible endpoint
genuine0.90cat0.66subst2.91Research and EvalsJavaScriptreadme pickBenchmarking Jev/Laya/GLM-5.3 Flash for System One-like tasks
genuine0.98cat1.00subst2.77Research and EvalsPythonreadme pickAutomated PR review pipeline using Jev (TypeSafe AI) as a millisecond decision layer over an LLM reviewer
genuine0.88cat0.97subst2.98Agent and Dev ToolingTypeScriptreadme pickNative vLLM serving for Jev decision models
genuine0.82cat0.98subst2.83Research and EvalsPythonreadme pickAutomated PR review pipeline using Jev (TypeSafe AI) as a millisecond decision layer over an LLM reviewer
genuine0.96cat0.97subst2.98Agent and Dev ToolingTypeScriptreadme pickFirst independent head-to-head benchmark of System One decision models (Laya vs Jev) on byte-identical inputs
genuine0.95cat1.00subst2.85Research and EvalsPythonreadme pick