Human-Agent-Society / reef
Infrastructure for continually self‑improving agents
Why this job: topics: llm-training, reinforcement-learning
What it does
Reef is the first open-source infrastructure for continual self-improving agents. It connects agent inference, feedback, learning, and versioned delivery. Use it to train model weights with Slime and SGLang, or improve an agent's harness, including its prompts, rules, and skills.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit today
- Stars
- 7,787
- +27 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.1.3
- Released 26 days ago
- Built with
- Python
- 97% of the code
Is it looked after?
- Contributors
- 6
- Last 90 days
- Issues
- 67% closed
- 126 still open
- Pull requests
- 775 merged
- 30 waiting
- Releases
- 5
- 5 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| rsi-gear / gear | 423 | 7 days ago | MIT | No downloads |
| aiming-lab / MetaClaw | 3,467 | 5 months ago | MIT | No downloads |
| rllm-org / rllm | 5,913 | 31 days ago | Apache-2.0 | No downloads |
More: languages, topics, project record and preview image
Languages
- Python 97%
- C++ 2%
- Shell <1%
- Dockerfile <1%
Topics
- agent-infrastructure
- ai-agents
- continual-learning
- inference
- llm
- llm-training
- reinforcement-learning
- self-improving-agents
Project record
- JobFine-tuning
- StatusFeatured
- Commits765
- Forks731
- Watching514
- Stars in 28 days+226
- CreatedAug 31, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026