Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.
Small, calibrated decision models you run on your own machine, plus the tooling to put them to work in AI agents.
New in 0.3.0: Jev-Style-2B-Decision-v3. It scores 73.6 % on the 231 public items of JevBench v1.4.1 (self-run with the official harness on the GGUF F16 build, not an official board entry), 9.5 points above the 0.8B and the highest among the Qwen3.5-2B-family systems on the board. Its lead over decider-2b (71.0 %) is inside the 95 % confidence interval, 42 of the 82 board systems score higher, and hosted Jev is well ahead at 86.6 %. Try it in your browser, or run it locally with jev-style serve --release 2b. The default release is still the 0.8B, so existing setups get the same model as before.
Jev-Style is a family of small decision models built on Qwen3.5. The current releases are Jev-Style-2B-Decision-v3 (1.27 GB at 4-bit) and Jev-Style-0.8B-Decision-v3 (0.53 GB at 4-bit, the default); both, with every build and demo, are in the v3 collection. You give a model text or JSON and some typed questions, and it returns a calibrated probability for every option in one forward pass. The server's API follows the public systemone request shape, so clients written for Jev-compatible servers can call your laptop instead.
This repository is the part that makes the model useful day to day:
- jev-style serve: a local API with a Playground and demos. It picks MLX on Apple silicon and PyTorch on CUDA or CPU; llama.cpp is optional. - Six agent skills: install with one npx skills add. They serve the model, call it, evaluate it on your own labels, replace LLM calls that only
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/lawrence3699--jev-style.html)
Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.
Sur-Cai/macos-computer-use-kitAX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions kept in code. Accessibi
shitianfang/jev-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 th
agent-chaperone/agent-chaperoneScreens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
F0Rextasy/omp-laya-judgeLocal Laya System-1 judge MCP server + skill for oh-my-pi: typed decisions in milliseconds, zero LLM tokens
abhishekswe/agent-fastpathJev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with ca
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.