memU

NevaMind-AI/memU

Personal memory across agents

Install

GitHub: NevaMind-AI/memU
Website: memu.pro
Stars: ★ 14.6k
Language: Python
Last push: Oct 23, 2026
Topics: agent-memory · harness · loop-engineering · mcp · memory · openclaw · openclaw-skills

Good for

Share one personal memory, stored as a wiki, across sessions, agents and devices
Automatically distill reusable Markdown skills from your agent history
Bring relevant memory or learned skills into a similar future task

Getting started

Get an API key from memu.so
Send your agent: Read https://memu.pro/SKILL.md, follow its instructions to install and configure memU, with your API key
To self-host, ask the agent to read the SKILL.md in the GitHub repo and follow it
To uninstall, ask the agent to follow the same SKILL.md; by default your memory store is kept

Before you install

The hosted version needs an API key from memu.so, and self-hosting needs an embedding key. It works with Codex, Claude Code, Cursor and others, but not Claude Chat or Cowork.

Summarized by AI from the project docs; check the official docs before relying on it.

Similar tools

open-code-reviewCommunity skills · ★ 48.2k
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
cogneeCommunity skills · ★ 32.7k
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
nanoclawCommunity skills · ★ 31k
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
baoyu-skillsCommunity skills · ★ 26.9k
SkillSpectorCommunity skills · ★ 21.4k
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.