GH Repository · AMAP-ML
SkillClaw
Let Skills Evolve Collectively with Agentic Evolver
- stars
- 2,616
- 30-day movement
- +196/day
- Related entries
- 60
- Connections
- 1
agent-appPythonagentpythonllmskill-learninghermesskillscontinual-learningagentic-aiopenclawai-agentcollective-intelligencellmsself-evolvingskill-evolution
SkillClaw is a Python project from AMAP-ML described as 'Let Skills Evolve Collectively with Agentic Evolver'. Based on its name and topics, it appears to be an agent app in which skills are learned and evolved over time through an evolving agent process, drawing on ideas of continual learning and collective intelligence.
You want an agent system where skills improve through continual, self-evolving learning rather than staying fixed.
Use it to
- Experiment with skill-learning agent workflows
- Explore continual learning for LLM agents
- Study collective skill evolution approaches
- Extend the Agentic Evolver for your own agents
For Researchers and developers building self-evolving LLM agents
- Role
- agent-app
- Language
- Python
- Licence
- MIT
- Forks
- 262
- Open issues
- 26
- Last push
- 2026-08-17
topicsskill-evolutioncontinual-learningagentic-aillmcollective-intelligenceself-evolving