AgentDB Learning Plugins

This is a reinforcement learning toolkit that plugs into AgentDB, giving you nine different RL algorithms ranging from Q-Learning to Decision Transformers. The real appeal here is the WASM-accelerated neural inference, which they claim speeds up training by 10-100x. You'd reach for this if you're building autonomous agents that need to learn from experience rather than just following rules. It's part of the ruflo suite from ruvnet, which has a solid GitHub presence at 57K stars. Fair warning though, both Socket and Snyk flagged security concerns, so audit the dependencies before you ship anything production-critical. Assumes you know your way around RL concepts already.

Install to Claude Code

npx -y skills add ruvnet/ruflo --skill "AgentDB Learning Plugins" --agent claude-code