memU
Lightweight memory system that gives Codex, Claude Code, Cursor and other agents a shared memory across sessions and devices and distills reusable skills.
Updated
✨ Try AgentScout's free AI image generator →Good for: memory for agents
Use cases
About memU
memU is listed in our memory & RAG category and is aimed at builders. Lightweight memory system that gives Codex, Claude Code, Cursor and other agents a shared memory across sessions and devices and distills reusable skills. Pricing, as the maker states it: Free and open source (Apache-2.0); hosted memory free per the maker. Maturity: Mature. We last checked the official link on 2026-10-20.
What is memU?
memU is a lightweight, agent-driven memory system from NevaMind AI that gives you one personal memory, stored as a readable Markdown wiki, across sessions, agents and devices. A scheduled background task captures useful knowledge from your agent sessions and distills reusable skills from your agent history, and relevant memory is brought back into later tasks.
It works with Codex and ChatGPT's Work mode, Claude Code, Cursor, OpenClaw, Hermes Agent, WorkBuddy and others on macOS and Windows; setup is a message to your agent pointing it at memU's SKILL.md with an API key from memu.so. The core memory logic is about 500 lines of open-source code, and the hosted cross-device service is described by the maker as free and unlimited.
Sources: the official README and our directory listing, checked 2026-10-20. Official site: memu.pro.
Who is memU for?
People who use several coding or desktop agents (for example Codex at work and Claude Code at home) and want them to share the same memory of their projects and preferences.
memU at a glance
- Open source: Yes (Apache License 2.0)
- GitHub: NevaMind-AI/memU · 14,553 stars (as of Oct 21, 2026)
Key features
- One shared memory across agents, sessions and devices
- Memory stored as an inspectable Markdown wiki with source-linked recall
- Automatic skill extraction from your agent history
- Tested adapters for Codex, Claude Code, Cursor, OpenClaw, Hermes Agent and WorkBuddy
- Install by sending your agent the SKILL.md link plus an API key
memU FAQ
What is memU?
memU is a lightweight, agent-driven memory system from NevaMind AI that gives you one personal memory, stored as a readable Markdown wiki, across sessions, agents and devices. A scheduled background task captures useful knowledge from your agent sessions and distills reusable skills from your agent history, and relevant memory is brought back into later tasks.
Who is memU for?
People who use several coding or desktop agents (for example Codex at work and Claude Code at home) and want them to share the same memory of their projects and preferences.
Is memU free?
memU's pricing, as the maker states it: Free and open source (Apache-2.0); hosted memory free per the maker. Check the official site for current plans.
Is memU open source?
Yes. memU is released under the Apache License 2.0, according to its GitHub repository.
Which agents are not supported?
The README lists ChatGPT's Chat mode and Claude's Chat and Cowork modes as not supported; use ChatGPT's Work mode or Claude Code instead.
What are alternatives to memU?
Similar tools include Claude-Mem, TencentDB-Agent-Memory, Acontext, Graphicle, Mnemosyne and ai-memory.
memU ratings and reviews
Be the first to rate memU: tap 1 to 5 stars below. A written review is optional.
memU alternatives
Other memory & RAG tools in our directory. See all memory & RAG tools →
Claude-Mem
Gives coding agents memory across sessions by capturing what they do, compressing it and feeding the relevant context back in later.
TencentDB-Agent-Memory
Team-level memory hub that turns conversations, docs and code into shared memory for agents.
Acontext
Memory layer that stores agent experience as reusable skills.
Graphicle
Graphicle, from KarLex AI, is a single local Rust program that gives Claude Code, Cursor, Codex and other MCP agents a code graph and memory, returning excerpts with file and line references from your code, docs and past sessions, with no account or telemetry.
Mnemosyne
Zero-cloud, SQLite-backed memory layer for Hermes, Claude Code, Cursor, Codex and custom agents with a single Python dependency.
ai-memory
Fabio Akita's open-source long-term memory layer for coding agents: one Rust binary that keeps plain-markdown project memory and typed handoffs shared across 20+ harnesses such as Claude Code, Codex, Cursor and Gemini CLI, so you can switch agents, machines or teammates without re-explaining the project.
Badge for makers
Built memU? Add this badge to your README or site. It links back to this page. About badges
