⬢github Python · 685 ★ +65 since we first saw it · pushed 2 d ago · Apache-2.0
Rizzo-AI-Academy/rizzo-flow
The open, local take on Jev: typed decisions from an LLM, without generating a single token
Rizzo Flow is an open-source, fully local alternative to TypeSafe's hosted Jev service. It turns unstructured state into typed, probabilistic decisions (yes/no, choices, scores) without generating text tokens, using fine-tuned Spark-X2.5 models on llama.cpp. It exposes a Jev-compatible HTTP API, so existing client code only needs its URL changed to localhost.
Why now: Fresh fine-tuned weights (25 Sept 2026) improved accuracy and probability calibration on the typed-decisions benchmark, and it's trending among newly starred repos as a local, open-weights answer to Jev.
Who it is for: Developers who want Jev-style typed LLM decisions running privately on their own GPU or CPU hardware.
Stars over our 93 snapshots: 620 to 685, since 22 h ago.
Where people talked about it
- ⬢github new repos, most starred 1 h ago
API: https://socialmediatrends-api.osmike.com/v1/repos/Rizzo-AI-Academy/rizzo-flow