Shanghua-Gao / 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.
Why this job: works in the areas we cover, but does not say which job it does
What it does
AI agents propose the hypotheses, register their predictions before spending GPU time, run the experiments, and retire their own champions when the evidence says to. Every release, and every experiment that failed on the way, is published with its numbers. The loop is the next version of AutoScientists.
Get started
pip install "rsi-jev[fast,vision] @ git+https://github.com/Shanghua-Gao/RSI-Jev"
rsi-jev serve v7.0-vl-4b --effort auto --port 8000 - Maintenance
- Active
- Last commit 2 days ago
- Stars
- 137
- +3 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest tag
- v7.0-VL-3B
- Released 5 days ago
- Built with
- HTML
- 64% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 42 merged
- 0 waiting
- Releases
- 11
- 12 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| nokia-applied-research / AnyJev | 1,604 | 22 days ago | Apache-2.0 | No downloads |
| TokenRhythm / NeoHorse | 1,702 | 47 days ago | Apache-2.0 | No downloads |
| receptron / laya | 1,067 | 26 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- HTML 64%
- Python 36%
- Jupyter Notebook <1%
- Shell <1%
Topics
- ai-agents
- autonomous-research
- decision-model
- jev
- llm
- recursive-self-improvement
- system-one
- typed-decisions
Project record
- JobOther AI tools
- StatusListed
- Commits245
- Forks12
- Watching2
- Stars in 28 days+20
- CreatedSep 22, 2026
- First seen by usNov 7, 2026
- CheckedNov 12, 2026