anthroos/openexp
Q-learning memory for Claude Code — your AI learns from experience. 16 MCP tools, hybrid retrieval, closed-loop rewards.
This project enhances your AI assistant (like Claude Code) by teaching it what actually works based on real outcomes. It takes in observations from your AI's daily tasks, like sales emails or code commits, and uses feedback from successful results to prioritize relevant memories. An AI agent, developer, or sales professional can then use this to ensure their AI always draws on the most effective past experiences.
Use this if you want your AI assistant to get smarter over time, learning which past decisions and strategies consistently lead to successful outcomes in your workflows.
Not ideal if you only need static memory storage for your AI without any outcome-based learning or prioritization of past experiences.
Stars
9
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 30, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/anthroos/openexp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ghostwright/phantom
An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure...
dograh-hq/dograh
Open Source Voice Agent Platform
gmickel/flow-next
Plan-first AI workflow plugin for Claude Code, OpenAI Codex, and Factory Droid. Zero-dep task...
joseairosa/recall
Persistent cross-session memory for Claude & AI agents. Self-host on Redis/Valkey, or use the...
lintsinghua/claude-code-book
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent...