whereismyai
memU
memU is an AI memory layer that provides shared and inspectable personal context across multiple AI agents.
memU is a personal memory layer designed to carry preferences, decisions, and learned skills across multiple AI agents, sessions, and devices. It connects tools like Codex, Claude Code, Cursor, OpenClaw, Hermes, and WorkBuddy through skill-driven host adapters. The system stores, embeds, and retrieves memory records without running LLM retrieval chains, allowing agents to decide what to remember. Users can keep every memory record inspectable and linked to its original source. It is built for developers and teams who want to maintain continuity across coding, personal assistance, knowledge work, and support workflows.
memU at a glance
- Best for: Software engineer
- Runs on: API, self-hosted
- Pricing: Freemium
- Released: July 2025
- Category: AI agent tool
- Website: memu.pro
Key features
- Shared memory across multiple agents
- Inspectable memory records
- Source-linked recall
- Skill-driven host adapters
- Managed cloud or self-hosted deployment
- Custom memory scope and retrieval behavior
Use it for
- Coding across multiple agents
- Carrying personal assistant preferences
- Preserving research context in knowledge work
- Maintaining continuity in support workflows
Companion to
Tools whose articles name memU as a companion, each with its job for them.
Alternatives to memU
- Mem0 — It provides drop-in persistent memory for AI agents without changing pipelines.
- Supermemory — Integrates long-term memory into AI coding agents with a single prompt.
- ReMe — It enables local-first, file-native long-term memory sharing across multiple AI agents.
- Memmy — Shares one persistent memory foundation across your different AI tools.
- MemMachine — Provides long-term persistent memory for LLM-based agents.
- claude-mem — It shares persistent, searchable agent memory across sessions and devices.
- Agentmemoryrepo — Enables agents to navigate memories like a wiki and share knowledge across sessions.
- MemOS — It delivers ultra-persistent memory, hybrid-retrieval, and token savings.
- MemPalace — Achieves high recall with local-first storage and zero API calls.
- Maximem — It delivers fast retrieval and structured memory across frameworks.
- memsearch — It shares continuous context across Claude Code, Codex, and other AI coding agents.
- Memori — Reduces LLM token usage and spend by over 97% with targeted recall.
All memU alternatives