imem
About
Set up a private AI memory vault in about a minute. No migration, no setup call, no card required.
Explore
A private memory for your AI, real human support, and your data always yours to take with you. Free includes hosted MCP and hosted AI embeddings; upgrade to Solo, Team, or Business when you need higher limits or more room.
A light private vault for getting imem installed and working.
- 1 private vault
- Hosted MCP
- Hosted AI embeddings
- 1,000 MCP calls/mo
- 500 searches/mo
- 100 writes/mo
- 50K embedding input tokens/mo
- 128MB vault cap
Free plan. Upgrade only when you need more room.
For the operator who lives in their AI tools all day.
- 25,000 MCP calls/mo
- 7,500 searches/mo
- 3,000 writes/mo
- 1M embedding input tokens/mo
- 1GB vault cap
14-day paid-plan trial. No card required to start.
For small teams standardizing memory across shared AI workflows.
- 125,000 MCP calls/mo
- 40,000 searches/mo
- 12,000 writes/mo
- 10M embedding input tokens/mo
- 5GB vault cap
- Priority setup support
14-day paid-plan trial. No card required to start.
For business use with onboarding, security review support, and top self-serve limits.
- 500,000 MCP calls/mo
- 150,000 searches/mo
- 50,000 writes/mo
- 50M embedding input tokens/mo
- 25GB vault cap
- Onboarding/security review support
14-day paid-plan trial. No card required to start.
For custom usage, security review, implementation planning, and procurement support.
- Custom usage
- DPA/security review
- Implementation planning
- Invoice and procurement support
No checkout. We'll scope the right plan with you.
Solo, Team, and Business are Stripe-backed self-serve plans with a 14-day no-card trial. Enterprise is handled by a human.
What people usually ask before they try imem
imem is a private memory and wiki for your AI tools. It keeps your notes in plain markdown, lets your tools read and write that memory through MCP, and gives you a web app to manage everything.
You connect imem with one URL, approve access, and start using it. MCP is the connection underneath; you do not need to learn it first.
Built-in memory stays inside one tool. imem gives you one shared memory your AI tools can all use, and your notes stay in plain files you can export anytime.
No. imem works in the web app and through your AI tools on its own. Obsidian is optional if you want to edit the same markdown files locally.
Free includes 1 private vault, hosted MCP, hosted AI embeddings, 1,000 MCP calls/month, 500 searches/month, 100 writes/month, 50K embedding input tokens/month, and a 128MB vault cap.
Yes. Your vault stays in plain markdown, so you can export it and take your data with you at any time.
Local Work Model for AI agents that learns from real outcomes.
Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.
Self-hosted MCP server giving AI agents persistent memory — Markdown source of truth, hybrid BM25+embedding search, typed graph relations.
MCP (Model Context Protocol) server that exposes 70 tools spanning cognitive memory, working memory, sessions, agents, the L0–L3 knowledge hierarchy, orchestration tasks, and training pipelines. The server speaks stdio and is consumed by Claude Desktop, Claude Code, OpenCodex, and any MCP-aware client.
mem0-mcp-server — exposes Mem0 persistent semantic memory as an MCP HTTP server; supports add/search/read/update/delete operations and semantic search for agent memory.
Personal memory layer for AI assistants. Store, search and recall preferences, decisions and facts — available from any MCP-compatible client.
A living memory that decays, learns, and evolves with your AI.
Hosted MCP memory across Claude Code, Cursor, ChatGPT and any MCP client. Community-hosted instance of the MIT-licensed MemPalace engine. EU-hosted, GDPR-compliant. Free tier with 200 memories.
Long-term memory system for AI agents with semantic search, context management, and multi-format storage.
Persistent AI memory: store, search, and recall knowledge across sessions
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
