DeepMem — MCP server for Claude Code, Codex and Cursor
Persistent memory for AI agents: facts are written once and recalled by meaning. Useful when context keeps vanishing between sessions.
claude mcp add --transport http deepmem https://deepmem.dev/mcpWhat DeepMem does
DeepMem is an HTTP memory server that speaks the Mem0 API. Under the hood: FastAPI in front of a Qdrant vector store, LLM fact extraction, hybrid retrieval (vector plus BM25, entity boost, time-decay), semantic caching and async batched distillation. Multi-tenant isolation comes from the user_id in the request body.
Two ways in. The client library: pip install deepmem-client, then swap one import line — from mem0 import MemoryClient becomes from deepmem import MemoryClient. Or run it as an MCP server: in Claude Code that is claude mcp add --transport http deepmem https://deepmem.dev/mcp. A dm_live-... key is only needed for the cloud; the self-hosted server runs in open mode with no key and no registration.
Some behaviour is worth knowing up front. With add(infer=True) the write is asynchronous — you get pending=True and an empty results list, and extracted facts land a few seconds later. There are no graph relations, so relations is always empty; retrieval is hybrid, not graph-based. reset is scoped to a single user_id and asks for confirmation.
What it helps with
- recall who the user is and what they were building last session
- keep root causes and dead ends across sessions
- store preferences without restating them every time
- run agent memory on your own box instead of someone else's cloud
- move a project off Mem0 by changing one import line
Example prompts for the agent
- Remember that I'm working on a FastAPI service and prefer pytest
- What do you know about me from previous sessions?
- Search your memory for the error we debugged last time
How to install DeepMem
Platform CLI: remote server
claude mcp add --transport http deepmem https://deepmem.dev/mcpPlatform CLI: remote server
codex mcp add deepmem --url https://deepmem.dev/mcpConfig file
{
"mcpServers": {
"deepmem": {
"url": "https://deepmem.dev/mcp"
}
}
}Config file
{
"servers": {
"deepmem": {
"type": "http",
"url": "https://deepmem.dev/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http deepmem https://deepmem.dev/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about DeepMem
How do I install DeepMem in Claude Code?
One command: claude mcp add --transport http deepmem https://deepmem.dev/mcp.
What does DeepMem do?
It turns conversations into long-term memory: an LLM extracts facts, they go into Qdrant, and later they are recalled by meaning. Agents reach them as tools.
How is DeepMem different from Mem0?
The API matches — same MemoryClient class, same method signatures, only the import line changes. DeepMem has no graph relations, and reset is per-user_id rather than account-wide.
