Modeljury
github.com/yassermanss/modeljury- Category
- Developer Tools
- Rank
- No. 2087Tools index
- Pricing
- Open Source
- Type
- TOOL
- Use case
- Models: Train & Run
- GitHub
- 1 stars
- Latest release
- v0.3.0
- Date
About
Modeljury is a Python library that asks several language models the same question and ships the answer when they agree. When they disagree it flags the decision for human review and returns the dissenting juror's reason. It works with any OpenAI-compatible endpoint and Claude, and the README reports benchmark results on 2,850 decisions, including cases where a single large model does better.
Tags
llmensemblevotinghuman-in-the-looppythonevaluation
Tech Stack
Python
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.