# Membase — full reference for AI readers > One memory. Every AI. Only yours. Membase is a long-term memory for you and your AI. Bring knowledge, preferences and decisions from conversations, files and connected apps into a lasting memory you and your AI can build on. You choose what to keep and who can access it. Membase is made by Unibase. Site: https://membase.ai · Docs: https://docs.membase.ai · App: https://www.app.membase.ai Parent: https://unibase.com (docs at https://docs.unibase.com) --- ## What problem it solves Preferences, research and decisions build up over time, spread across conversations, files and apps. Membase brings them into a lasting memory you can update and put to use with your AI. --- ## The model Three nouns, and the same tool table behind every surface: - **Container** — a scope. One per project, client or part of your life. Access is granted per container, so an agent can be given a project without being given everything else. - **Memory** — a fact, a note, a saved answer. You can read, correct, delete and export any of them. - **Document** — a file or page you put in, which becomes retrievable alongside memories. Two verbs: - **`search`** returns passages, each with the container it came from. It is retrieval, not generation — nothing is synthesised. - **`ask`** returns an answer written over those passages, for when you want the agent to answer rather than to read. --- ## How to use it ### As a person - **Web app** — https://www.app.membase.ai. Sign in and the memory is there. Nothing asks for a wallet. - **Chrome extension** — syncs conversations from ChatGPT, Claude, Gemini, Grok, DeepSeek and Kimi, and saves web pages. Encrypted on the device with a wallet-derived key before anything leaves it. - **Desktop app** — coming soon; local memory and offline search are planned. ### As a developer - **MCP** — point any MCP client at `https://api.app.membase.ai/mcp-http`. One command connects Claude Code; Cursor, ChatGPT and other clients take the same URL. Sign in once; the consent screen asks which memories the client may reach. - **REST API** — the same tool table over HTTP. - **SDKs** — `pip install membase-ai` (Python), `npm i membase-ai` (TypeScript). One client, one key. Tools available through MCP: `search_memories`, `ask_agent`, `add_memory`, `add_document`, `list_containers`, `get_profile`. --- ## What makes it different Membase is a product **and** an API over the same memory: 1. **You can see it.** Every fact it holds is readable, editable and deletable, and the whole thing is exportable in one request. 2. **Several agents share one memory.** Not one memory per app. Scoping decides which agent reaches what, and revoking takes effect at once. 3. **It reaches the assistants you already use**, through the extension, rather than only the agents you write. --- ## Benchmarks These measure the **memory engine**, not the product as a whole, and are reproducible from the published benchmark repository. | Benchmark | Accuracy | Mean context tokens | Against full context | |---|---|---|---| | LoCoMo | 93.1 | 6,562 | ~20k (3× less) | | LongMemEval | 92.6 | 8,970 | ~103k (11× less) | | DMR | 92.2 | 1,602 | — | --- ## Storage and privacy - The hosted service stores and processes the sources you provide to build and retrieve memory. Each account’s memory runs in an isolated environment. - The hosted service is not end-to-end encrypted. The extension has its own privacy policy describing its data handling: https://membase.ai/privacy. - Unibase DA is available as a verifiable storage backend through the protocol SDK; the hosted product does not depend on it. --- ## Relationship to Unibase Unibase publishes an open protocol stack: **AIP** for ERC-8004 agent identity and cross-platform interoperability, **Unibase Pay** for x402 payments agents settle themselves, and **Unibase DA** for verifiable data storage. **UB** is the network token. Membase is a Unibase product and has its own site. It does not require any of the protocols to run. - Unibase: https://unibase.com - AIP: https://unibase.com/aip - Unibase Pay: https://unibase.com/pay - Unibase DA: https://unibase.com/da --- ## Common questions **What is Membase?** Membase is a long-term memory for you and your AI. Bring knowledge, preferences and decisions from conversations, files and connected apps into a lasting memory you and your AI can build on. You choose what to keep and who can access it. **How do I get started?** Open Membase, create a memory and add your first source. Then connect an AI tool to use it. Install the Chrome extension if you want to save and reuse context while browsing. **Which AI tools can I connect?** The Chrome extension supports ChatGPT, Claude, Gemini, Grok, DeepSeek and Kimi. Coding tools such as Claude Code, Cursor and Codex connect through MCP. Custom agents can use MCP, the REST API, or the Python and TypeScript SDKs. **Does Membase save things automatically?** You choose how information is added. The extension supports conversation sync and individual saves. You can also upload files, connect supported apps or let authorized agents add knowledge. **Can I keep personal and work memories separate?** Yes. Create separate memories for different projects, clients or areas of your life, then choose which ones each connected tool can access. **Can I correct, delete or export my memory?** Yes. You can review and correct saved information, delete memories you no longer need, and export your data. You can also revoke a connected tool’s access. Removing a source stops future updates; delete the memory separately to remove what it learned. **How does Membase handle my data?** The hosted service stores and processes the sources you provide to build and retrieve your memory. Each account’s memory runs in an isolated environment. The hosted service is not end-to-end encrypted. The Chrome extension has a separate privacy policy describing its data handling. **Does Membase work offline?** The web app and Chrome extension require an internet connection. Offline memory search is planned for Membase Desktop, which is coming soon.