7 entries — sorted by GitHub stars.
An experimental autonomous multi-agent system framework built on top of OpenClaw.
An OpenClaw agent that improves its own SKILL.md based on usage feedback — the self-upgrading agent pattern.
An agent that evolves its own capabilities by analysing task patterns and rewriting its skill config.
Enable OpenClaw to run proactively in the background — monitoring conditions and initiating actions without user prompts.
Let OpenClaw agents autonomously navigate websites, click links, and extract structured data.
An OpenClaw agent that actively requests feedback to improve its task performance over time.
Core headless browser engine for OpenClaw agents — the foundation for all browser-based automation skills.