Built with Open reimplementations
jev-style
Local classification, routing, and scoring for AI agents, with option probabilities. Text + images, Python, MCP and agent skills.
24 ★ on GitHub
What it is
Small, calibrated decision models you run on your own machine, plus the tooling to put them to work in AI agents.
The homepage listed on the repository, jevstyle.com, puts it like this: Classify text, route requests, and score fixed choices in Python. Use the free hosted API, or run small open models on CPU, CUDA, or Apple silicon.
What the README says it does
- 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 return a label, add a guard to Claude Code, and add the MCP tools.
- A Claude Code guard: a PreToolUse hook where the local model checks every tool call before it runs and answers allow, ask or deny.
- An MCP server: tools decide, noul, choice and score for Claude Code, Cursor, Codex and any other MCP client.
- jev-style eval: measures accuracy and calibration on your own labelled data, and reports how many decisions you can automate at a 1, 5 or 10 % error budget.
From the project’s README.
Where the decision sits
jev-style calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.
Models it references: Jev, decider-2b, Jev-Style-0.8B-Decision-v3-GGUF, Jev-Style-0.8B-Decision-v3-MLX, Jev-Style-2B-Decision-v3-GGUF, Jev-Style-2B-Decision-v3-MLX, Jev-Style-2B-Decision-v3, Jev-Style-Qwen3.5-2B-Decision-GGUF, Jev-Style-Qwen3.5-2B-Decision-v2-GGUF, JevK5-9B, JevK5, laya, decider-2b.
How active it is
Created 2026-09-25, last pushed 2026-11-01, 24 stars and 2 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.