rsi-gear / gear
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
Why this job: topics: llm-training, reinforcement-learning
What it does
Gear is an open-source optimization framework for improving AI agent performance on real-world tasks.
Get started
npm install --global rsi-gear@latest agent-hitch@latest @deepseek-ai/dsh@latest
hitch eval setup harbor - Maintenance
- Active
- Last commit 7 days ago
- Stars
- 423
- +21 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.2.2
- Released 7 days ago
- Built with
- TypeScript
- 50% of the code
Is it looked after?
- Contributors
- 5
- Last 90 days
- Issues
- 52% closed
- 10 still open
- Pull requests
- 66 merged
- 27 waiting
- Releases
- 7
- 7 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 |
|---|---|---|---|---|
| Human-Agent-Society / reef | 7,787 | today | Apache-2.0 | No downloads |
| aiming-lab / MetaClaw | 3,467 | 5 months ago | MIT | No downloads |
| metaevo-ai / harness-zero | 139 | 14 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- TypeScript 50%
- Python 44%
- JavaScript 6%
- Shell <1%
Topics
- meta-learning
- reinforcement-learning
- rsi
- ai-agents
- continual-learning
- infrastructure
- llm-training
- agent-harness
- harness-optimization
- recursive-self-improvement
- rsi-gear
- rsigear
Project record
- JobFine-tuning
- StatusFeatured
- Commits303
- Forks39
- Watching3
- Stars in 28 days+279
- CreatedAug 18, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026