csuzngjh/principles
Evolutionary agent framework that captures failures as pain signals, distills them into reusable principles, and applies learned wisdom to avoid repeating mistakes — built as an OpenClaw plugin
Source: https://github.com/csuzngjh/principles
Discovered from GitHub repositories pushed in the last 24 hours for agent skills, Claude/Codex/Gemini workflows, MCP tooling, and adjacent AI-agent automation.