Built with Open reimplementations
AnyJev
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
1.6k ★ on GitHub
What it is
English · 简体中文 · ⚡ Serve it · 📊 Results · 🧭 Roadmap · 📖 Levels
The homepage listed on the repository, pypi.org, puts it like this: AnyJev: Jev-style typed decisions with probabilities from open LLMs: a training-free readout of any model, and the self-distilled Tacit models. Not affiliated with TypeSafe AI.
Where the decision sits
AnyJev runs its own weights or its own runtime rather than calling a hosted API, so its decisions do not depend on a vendor being up or on a key being funded. The trade is that the model is now yours to keep current.
Models it references: laya.
How active it is
Created 2026-09-21, last pushed 2026-10-21, 1,550 stars and 177 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.