Awesome Jev

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)

Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)

Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.

A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.

JevBench by Benchmark Heaven: benchmark and leaderboard for AI decision models, measuring typed decision accuracy, calibration, latency and cost.

Typed-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.

No description provided.

Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.

ReflexBench — open benchmark and evaluation harness for System One models and typed decision engines

Benchmarking Jev/Laya/GLM-5.3 Flash for System One-like tasks

jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.

Claude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything else

Independent calibration audits for AI judges. The Moody's for AI judgment.

Open-source, local decision models inspired by TypeSafe’s Jev and System One - built on Qwen3 for NVIDIA DGX Spark.

Open 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.

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

AI-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.

A 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.

Super fast Jev like server, model agnostic, working with any OpenAI compatible endpoint

A testable spec and conformance suite for Jev-compatible (TypeSafe System One) API servers, with a normalising proxy, a reference mock and a GitHub Action.

Automated PR review pipeline using Jev (TypeSafe AI) as a millisecond decision layer over an LLM reviewer

Native vLLM serving for Jev decision models

Automated PR review pipeline using Jev (TypeSafe AI) as a millisecond decision layer over an LLM reviewer