← Back to all projects
Mem0
Long-term memory layer that persists across agent sessions
Apache-2.0
What is Mem0?
Extracts durable facts from a conversation and retrieves the relevant ones on later runs, instead of replaying an ever-growing transcript into the context window. Useful wherever an assistant should remember a user between sessions. What gets stored is model-decided, so verify the extraction quality on your own data before relying on it.
What can you do with Mem0?
- Carry user facts between sessions —
memory.add(messages, user_id=...)extracts durable facts from a conversation, andmemory.searchwith auser_idfilter andtop_kreturns only the ones the next prompt needs. - Turn on hybrid retrieval — Installing
pip install mem0ai[nlp]together with the spaCyen_core_web_smmodel adds BM25 keyword matching and entity extraction on top of dense vector search. - Inspect what got stored — The CLI from
npm install -g @mem0/cligivesmem0 addandmem0 searchwith--user-id, so you can check what the extractor actually kept before trusting it in an application. - Self-host the memory server —
make bootstrapin theserverdirectory starts the stack, creates an admin and issues the first API key; auth is on by default, withAUTH_DISABLED=truereserved for local development. - Wire Mem0 into a repo — Pipeline skills added via
npx skills add—/mem0-integratethen/mem0-test-integration— run a test-first integration inside Claude Code, Cursor and other tools supporting the skills standard.
Before you choose Mem0
- The extra search step relies on an English-only language model, so on Japanese, Chinese, Korean or Arabic it finds nothing. No error appears — search quietly falls back, without the accuracy you installed it for.Reported in#4884
Star history
15 Aug to 30 Oct · +4.8k
63.3k68.1k
Frequently asked questions
Is Mem0 free for commercial use?
Mem0 is released under the Apache-2.0 licence — OSI-approved open source, which permits commercial use.
How can Mem0 be deployed?
Mem0 is available as Self-hosted / Managed cloud.