Official description7 sourcesMCP servers8d ago
unibaseio/membase-mcp
๐ โ๏ธ - Save and query agent memory in a distributed way with Membase
View on GitHub โDirect link ยท no redirect page
Config template (adjust for your client)
claude mcp add membase-mcp -- npx -y membase-mcp
A pasteable skeleton generated from the repository name. Check the project README for the exact package and arguments.
- Star count
- 24 โ ยท unibaseio/membase-mcp ยท read from the repository page ยท (checked 2026-10-16 20:00:20)
- Source
- collected from the punkpeye/awesome-mcp-servers list ยท type: MCP server
- Harvest history
- first seen 2026-10-09 ยท last seen 2026-10-16 ยท seen 32ร ยท listed by 7 sources
- Score
- score 703 ยท 24 โ ยท 7 sources ยท mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP ๆๅก. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
unibaseio/membase-mcp๏ผfirst catalogued 2026-10-09๏ผlast seen 2026-10-16ใThere is no official certification or quality rating here โ we record sources and dates only.Third-party quality signals
Membase
ไปฅไธๆๅฝ่ช่ฏฅไปๅบ็ README๏ผ็ๆฎต๏ผ ยท ๅจ GitHub ่ฏปๅฎๆด README โ
One memory. Every AI. Only yours.
Teach it once. Every AI remembers.
Website ยท
Docs ยท
Web app ยท
Discord ยท
X
Membase is the memory layer for AI agents. It keeps one memory for everything you and your agents
know, and every AI you use reads it.
You stop re-explaining yourself each time you switch models or tools.
- **Add.** Facts, documents, web pages and chat exports from Claude or ChatGPT go into one memory.
- **Manage.** Containers keep projects apart; search it, ask it questions, forget what should go.
- **Use.** Your code, Claude Code, Cursor, Codex and ChatGPT read the same memory through the SDK or MCP.
This repository is the developer side: Python and TypeScript clients, the membase command line
and an MCP server. The memory lives in your Membase account, which the
web app and browser extension also fill, or on your machine with
unibaseio-membase[local].
Write once, read from any AI
Recordings: Python SDK (57 s) ยท
Claude Code (1 min 33 s). The answer above is illustrative.
Accuracy
93.1% on LoCoMo, 92.6% on LongMemEval_S and 92.2% on DMR, using about 3ร fewer tokens than the full
history on LoCoMo and 11ร fewer on LongMemEval_S. Method and results: membase.ai/research
Quickstart
Every method, its REST route and MCP tool, and the access it needs: SDK reference.
The Python package is unibaseio-membase (import membase); membase on PyPI is unrelated.
Command line
Without --local (or --store DIR, both before the command) commands use the hosted API; agent,
import and serve need unibaseio-membase[local].
MCP
Hosted without the header, the connection signs you in and is read-only. Setup for Claude, ChatGPT,
Cursor, Codex and other clients: Connect your AI.
Docs
- SDK reference: methods, REST routes, MCP tools, access levels
- Memory operations: containers, documents, memories, profile, ask
- Authentication: keys and what each one can reach
- Connect your AI: per-client MCP setup
- Local engine: what it stores, membase serve, settings
License
Teach it once. Every AI remembers.
Website ยท
Docs ยท
Web app ยท
Discord ยท
X
Membase is the memory layer for AI agents. It keeps one memory for everything you and your agents
know, and every AI you use reads it.
You stop re-explaining yourself each time you switch models or tools.
- **Add.** Facts, documents, web pages and chat exports from Claude or ChatGPT go into one memory.
- **Manage.** Containers keep projects apart; search it, ask it questions, forget what should go.
- **Use.** Your code, Claude Code, Cursor, Codex and ChatGPT read the same memory through the SDK or MCP.
This repository is the developer side: Python and TypeScript clients, the membase command line
and an MCP server. The memory lives in your Membase account, which the
web app and browser extension also fill, or on your machine with
unibaseio-membase[local].
Write once, read from any AI
Recordings: Python SDK (57 s) ยท
Claude Code (1 min 33 s). The answer above is illustrative.
Accuracy
93.1% on LoCoMo, 92.6% on LongMemEval_S and 92.2% on DMR, using about 3ร fewer tokens than the full
history on LoCoMo and 11ร fewer on LongMemEval_S. Method and results: membase.ai/research
Quickstart
Every method, its REST route and MCP tool, and the access it needs: SDK reference.
The Python package is unibaseio-membase (import membase); membase on PyPI is unrelated.
Command line
Without --local (or --store DIR, both before the command) commands use the hosted API; agent,
import and serve need unibaseio-membase[local].
MCP
Hosted without the header, the connection signs you in and is read-only. Setup for Claude, ChatGPT,
Cursor, Codex and other clients: Connect your AI.
Docs
- SDK reference: methods, REST routes, MCP tools, access levels
- Memory operations: containers, documents, memories, profile, ask
- Authentication: keys and what each one can reach
- Connect your AI: per-client MCP setup
- Local engine: what it stores, membase serve, settings
License
- Source
- awesome ยท https://github.com/unibaseio/membase-mcp
- Browse by field
- MCP servers
- Traction
- 24 โ
- added
- yesterday
More in MCP servers
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.