rizzo-flow

What it is

The open, local take on Jev: typed decisions from an LLM, without generating a single token

The homepage listed on the repository, rizzo-ai-academy.github.io, puts it like this: rizzo-flow: la versione open e locale di Jev. State in ingresso, decisioni tipizzate con probabilità in uscita: bool, classe, score, numero. 100% locale, API compatibile con Jev.

Getting started

From the README:

git clone https://github.com/Rizzo-AI-Academy/rizzo-flow && cd rizzo-flow
uv sync --locked          # seconds: four small Python packages
uv run rizzo download     # llama.cpp for this machine + Rizzo Flow 4B Q8_0 (~4.4 GB)
uv run rizzo serve        # → http://127.0.0.1:8017/playground

Where the decision sits

rizzo-flow 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.

How active it is

Created 2026-09-21, last pushed 2026-09-25, 953 stars and 62 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.