Membase

com.membasePublished by membase.comOfficial publisherv1.0.1Updated Nov 7, 2026

Long-term memory for you and your AIs: search memories, read the profile, add facts and documents.

VerifiedStreamable HTTPWeb executableKnowledge & MemoryAI & ML

Overview

AI-generated overview

Membase is a hosted long-term memory layer that lets an AI assistant search stored memories, read a user profile, and add facts and documents shared across…

What you can do
  • Search and question stored memories, including asking questions across them
  • Add facts, documents, web pages and imported chat exports to a memory
  • Read profile facts about the user and list the memories a key can reach
  • Organize memories by project and remove entries that should be forgotten
  • Ingest and search media such as photos and video in the local variant
When to use it
Useful when you switch between models or coding tools and want each one to recall the same facts, project notes and documents instead of re-explaining context. Also fits when you want a searchable personal or project memory that assistants can query.
Requirements
Remote endpoint at api.app.membase.com over streamable HTTP with OAuth sign-in; a Membase account. The hosted connection can also use a bearer API key (MEMBASE_API_KEY) for read-write access. Local and media variants are Python packages needing Python 3.10+ (3.12/3.13 for local) and, for local, an OPENAI_API_KEY.
Before you install
Hosted connections without a key sign in and are read-only, so writes need a key with a write target. Adding memories sends your facts, documents and chat exports to Membase's servers. Removal requires explicit confirmation, and a key reaching several memories needs MEMBASE_WRITE_TARGET to know where writes land.

Installation

In SourceWeft

  1. Open Membase in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.membase%2Fmembase/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "membase": {
      "type": "http",
      "url": "https://api.app.membase.com/mcp-http"
    }
  }
}

README

[Membase]

Membase

One memory. Every AI. Only yours.
Teach it once. Every AI remembers.

[PyPI] [npm] [MIT]

Website · Docs · Web app · Discord · X

[Add sources, manage one memory, use it from every AI and app]

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. Memories keep projects apart; search them, ask them 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

[Your app writes a memory; any AI reads it, here Claude Code]

Recordings: Python SDK (57 s) · Claude Code (1 min 33 s). The answer above is illustrative.

Accuracy

[LoCoMo 93.1%, LongMemEval_S 92.6%, DMR 92.2%]

93.1% on LoCoMo, 92.6% on LongMemEval_S and 92.2% on DMR, using about 3× fewer tokens than the full history on LoCoMo and 11× fewer on LongMemEval_S. Method and results: membase.com/research

Quickstart

[Hosted, local in process, or local over HTTP]

bash
pip install unibaseio-membase              # hosted · Python 3.10+ · needs MEMBASE_API_KEYpip install 'unibaseio-membase[local]'     # local  · Python 3.12 or 3.13 · needs OPENAI_API_KEYpip install 'unibaseio-membase[media]'     # local + photos, videos and audionpm install @unibaseio/membase              # TypeScript · Node 18+npm install -g @unibaseio/membase-cli       # the `membase` command (hosted) without Python
python
from membase import Membase
m = Membase()                    # hosted# m = Membase(local=True)        # local, in ~/.membase
m.memories.add("We picked Postgres for the ledger service.")   # a factm.search("what database is the ledger on?")                    # {"items": [...], "partial": [...]}m.add("Design notes …", custom_id="design-1")                   # a documentm.profile_facts.list()                                         # who the user is (Your profile ticked)m.capabilities()                                               # what this key may do, and the rules

No call names a Memory: reads cover every Memory the key reaches, and writes land in its write target (a key that reaches several Memories and has none is refused with WriteTargetRequiredError). Ids are typed (mem_… a fact, doc_… a document, med_… a photo or video), lists are {items, has_more, partial}, and a removal without confirm=True raises ConfirmationRequiredError. Local memory answers the same routes with the same shapes.

Every method, its REST route and MCP tool, and the access it needs: SDK reference. Upgrading from 0.3: see the changelog. The Python package is unibaseio-membase (import membase); membase on PyPI is unrelated.

Command line

bash
membase --local add "We picked Postgres for the ledger"membase --local search "what did we pick for the ledger?"membase --local memories listmembase --local ask "Which database is the ledger on?"membase --local import ~/Downloads/claude-export.json     # Claude, ChatGPT, markdown or JSON chatsmembase --local agent ingest trace.json --agent codermembase --local agent search "fix flaky deploy" --agent codermembase --local media add ~/Movies/trip.mp4                # shots, speech and speakersmembase --local media search "someone skiing"   # any language

Without --local (or --store DIR, both before the command) commands use the hosted API; agent, import and serve need unibaseio-membase[local], and media add and media ask (local only) need unibaseio-membase[media]: see Media memory. A local store with several Memories writes where MEMBASE_WRITE_TARGET names.

MCP

[MCP clients, hosted or local server, same tools]

bash
claude mcp add membase -- membase --local mcp                                   # localclaude mcp add --transport http membase https://api.app.membase.com/mcp-http \  --header "Authorization: Bearer $MEMBASE_API_KEY"                             # hosted

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.

Gemini CLI, as an extension (it signs you in on first use; /mcp auth membase signs in again):

bash
gemini extensions install https://github.com/unibaseio/membase

Cline: add the server to cline_mcp_settings.json; llms-install.md has the entry, with and without a developer key.

Docs

License

MIT; see LICENSE. unibaseio-membase[local] also installs unibaseio-membase-core, the compiled engine, under its own Unibase license.

Source: README.md at commit ae41a32

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.1LatestNov 7, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Membase integrations

Membase

ai.membase

Membase is a hosted long-term memory layer that lets an assistant search, read, add and manage shared memories, documents and a profile across AI tools.

Streamable HTTPWeb executableAuth
Knowledge & MemoryCredential requiredOct 24, 2026