zhulinchng/jevper
Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients: probabilities and confidence instead of prose
About the project
A classification wrapper over OpenAI-compatible clients: instead of prose it returns typed questions (noul, choice, score) with probabilities and confidence. Works with any client exposing responses.create or chat.completions.create, including a self-hosted llama.cpp server.
Useful for
- Classify support tickets by intent with probabilities via logprobs
- Rate review sentiment on a Score scale with model confidence
- Switch classification to a self-hosted llama.cpp server without code changes
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 10 stars so far today, about 13 expected by the end of the day.
- The repository is 0 days old and already has 10 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Show HN: Jevper – the Jev interface on top of any OpenAI-compatible model” — 9 points, 4 h ago.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 10
- Today
- 10 · ≈ 13 by evening
- Forks
- 1
- Issues and pull requests
- 0
- Watchers
- 0
- Language
- Python
- License
- Apache-2.0
- Latest release
- v0.2.1 · September 23, 2026
- Created
- September 23, 2026
- Last push
- September 23, 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.
Hacker News discussions
- Show HN: Jevper – the Jev interface on top of any OpenAI-compatible model9 points, September 23, 2026
Spotted in
- September 23, 2026Spotted on Hacker News
Similar by description
-
2.1
kshetrajna12/reflex
An open decision model: given a state (text, JSON, or image) and typed questions, it returns calibrated probabilities over fixed answer options. Runs on top of Qwen3.5 and answers with numbers instead of free text.
-
3.6
razorback16/openjev
An open-source "System One" decision server on DiffusionGemma: send a state and typed questions (yes/no, choice, score) and get probabilities plus confidence in tens of milliseconds, with no text generated.…
-
2.7
kraayenjon/awesome-jev
A curated list of resources for Jev, TypeSafe AI's System One model that returns typed decisions (Choice, Score, Noul) with calibrated probabilities instead of generated text. Aimed at developers integrating Jev into…
-
4.8
receptron/laya
TypeScript wrapper for running the open-source Laya System-1 decision model via ONNX Runtime: takes a state and typed questions, returns answers with calibrated probabilities in one forward pass.
-
4.9
Rizzo-AI-Academy/rizzo-flow
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…
-
4.9
wfzyx/von
An open-source non-autoregressive System One decision model for classification, intent routing, and guardrail validation without text generation, with calibrated probabilities and sub-25ms latency.