Build and run agents you can see, understand and trust.
RSI-Jev
Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.
Project facts
- Relationship to Jev
- Jev application
- Evidence
- Documented
- Language
- Python
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-22
- GitHub stars
- 4
- Evidence checked
- 2026-09-26T23:19:40.000Z
- Metadata checked
- 2026-09-26T23:19:40.000Z
- Check status
- current
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
[Jev]-style *System One* models.** AI agents propose the
Evidence commit: bbcd82bcdcc1781db01f4e6b17edd4d29a914fa8
Discovered through: github-search.
How we review →