Clawland-AI/Geneclaw
Self-evolving AI agent framework with 5-layer safety gatekeeper. Agents observe failures, propose fixes, and safely apply them. Built on HKUDS/nanobot.
This is a framework for developers to create AI agents that can learn from their mistakes and improve themselves. It takes in observations of agent failures, diagnoses the problem, and proposes fixes. Developers then receive a suggested update to the agent's code, which can be reviewed and safely applied, making the AI agent smarter over time.
Use this if you are a developer building AI agents and want them to automatically identify and correct their own errors, with human oversight.
Not ideal if you need a plug-and-play solution for non-developers, or if you require an AI agent that operates without any human intervention in its learning process.
Stars
22
Forks
4
Language
Python
License
MIT
Category
Last pushed
Feb 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Clawland-AI/Geneclaw"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
arielshad/balagan-agent
Chaos Engineering for AI Agents
suryast/agent-taxonomy
🧬 Evolutionary taxonomy and self-improvement framework for AI agents — Lamarckian inheritance,...
evoplex/evoplex
Evoplex is a fast, robust and extensible platform for developing agent-based models and...
adrianwedd/AI-SWA
SelfArchitectAI - A self-evolving software architect agent that reasons about its own design,...
MrTsepa/autoevolve
AI agent evolving strategies through automated self-play overnight. Generic framework with...