Rizzo-AI-Academy/rizzo-flow
The open, local take on Jev: typed decisions from an LLM, without generating a single token
About the project
A local-first implementation of the Jev idea: an LLM returns typed decisions (boolean, choice, score, numeric) with probabilities in a single forward pass, without generating tokens. Compatible with the TypeSafe HTTP API.
Useful for
- Replace parsing of LLM JSON answers with typed decisions and probabilities
- Run a local decision service and point TypeSafe API code at localhost
- Classify support tickets by department and urgency via POST /v1/systemone
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 126 stars so far today, about 167 expected by the end of the day.
- The repository is 0 days old and already has 124 stars.
- Top new repositories this week: #154.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 124
- Stars in a day
- 167
- Forks
- 4
- Issues and pull requests
- 0
- Watchers
- 2
- Language
- Python
- License
- Apache-2.0
- Created
- September 21, 2026
- Last push
- September 21, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 21, 2026Top new repositories this week: #154
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/Rizzo-AI-Academy/rizzo-flow)Similar projects
-
8.7
mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.
-
8.5
jaredpalmer/kev
kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.
-
7.3
mizorewww/laya-coreml
Local port of the Laya model to Apple Core ML and Neural Engine: returns typed decisions (choice, score, yes/no) without token generation, with speed and energy benchmarks.
-
7.1
FareedKhan-dev/train-llm-from-scratch
Educational project: a from-scratch PyTorch Transformer plus a full LLM training pipeline — from raw text through SFT, reward modeling, PPO/DPO/GRPO to chat, without transformers, trl or peft.
-
7.1
TheoLeeCJ/SemIf
An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.
-
6.8
volotat/mini-AGI
A byte-level continual-learning language model that assembles its own architecture, trains from scratch on a single 8 GB VRAM GPU, and keeps learning from everything it reads. An experiment showing continual learning…