FOR DEVELOPERS
Long-term memory for your apps and agents.
Build on user preferences, accumulated knowledge and past decisions. Add and retrieve memory through MCP, REST, Python or TypeScript, with scoped access.
- container
- A memory space for a project, client or area of your life. Scope each credential to the containers it needs.
- memory
- A saved fact or note inside a container.
- document
- A file or page added to a container for background processing and retrieval.
search_memories
Search is retrieval
Returns relevant passages with their source containers, ready to include in your own prompt.
ask_agent
Ask a question
Returns an answer from the memory agent using the knowledge it can access.
1# pip install membase-ai2# export MEMBASE_API_KEY="mbk_..." (Connect > Developer keys in the app)34from membase import Membase56client = Membase()78# Remember something9client.add(10 "Call notes with Acme: they want SSO before the pilot.",11 container="mv-...",12)1314# Search returns relevant passages. Use client.ask() for an answer.15hits = client.search("what does Acme need before the pilot", limit=5)16print(hits["results"][0]["content"])