# Membase

> Persistent, shared memory for your AI agents.

## Docs

- [Changelog](https://docs.membase.so/changelog/index.md): Latest updates, new features, and improvements to Membase. Stay up to date with product releases, bug fixes, and new integrations.
- [ChatGPT](https://docs.membase.so/connectors/agents/chatgpt.md): Connect Membase to ChatGPT as a custom app using MCP. Give ChatGPT persistent memory that remembers your preferences and context across every conversation.
- [Claude Code](https://docs.membase.so/connectors/agents/claude-code.md): Connect Membase to Claude Code with the Membase Claude Code plugin. Add persistent memory, wiki retrieval, slash commands, hooks, and project-aware context to your coding sessions.
- [Claude](https://docs.membase.so/connectors/agents/claude-desktop.md): Connect Membase to Claude as a custom connector. Give Claude persistent memory that carries your context, preferences, and decisions across conversations.
- [Codex](https://docs.membase.so/connectors/agents/codex.md): Connect Membase to Codex via CLI setup. Give Codex persistent memory for coding preferences, project context, and past decisions.
- [Cursor](https://docs.membase.so/connectors/agents/cursor.md): Connect Membase to Cursor with one-click MCP setup. You can also use the Membase Cursor plugin for packaged rules and skills.
- [Gemini CLI](https://docs.membase.so/connectors/agents/gemini-cli.md): Connect Membase to Gemini CLI with a single command. Give Gemini persistent memory across sessions for smarter, context-aware responses.
- [Generic MCP URL](https://docs.membase.so/connectors/agents/mcp-url.md): Connect any MCP-compatible AI client to Membase using a generic server URL. Works with any tool that supports the Model Context Protocol.
- [OpenCode](https://docs.membase.so/connectors/agents/opencode.md): Connect Membase to OpenCode via CLI setup. Add persistent memory to OpenCode for context-aware coding that remembers your preferences across sessions.
- [Poke](https://docs.membase.so/connectors/agents/poke.md): Connect Membase to Poke via MCP integration. Add persistent, cross-session memory to your Poke AI assistant for smarter, context-aware responses.
- [VS Code](https://docs.membase.so/connectors/agents/vscode.md): Connect Membase to VS Code with one-click install. Add persistent memory to your VS Code AI assistant for context-aware coding across sessions.
- [App Integrations](https://docs.membase.so/connectors/apps.md): Connect external applications to Membase. Enrich your agents' memory with data from Gmail, Calendar, Slack, and more.
- [Hermes Agent](https://docs.membase.so/connectors/hermes.md): Add persistent long-term memory, wiki retrieval, and built-in memory mirroring to Hermes Agent with Membase's hybrid vector + knowledge graph memory provider.
- [Obsidian](https://docs.membase.so/connectors/obsidian.md): Import an Obsidian vault into Membase.
- [OpenClaw](https://docs.membase.so/connectors/openclaw.md): Add persistent long-term memory to OpenClaw across Telegram, WhatsApp, Discord, Slack, and more with Membase's universal memory layer.
- [Attached vs Universal](https://docs.membase.so/core-concepts/attached-vs-universal.md): Understand why AI memory should be shared across agents, not isolated within individual tools. Learn the difference between attached and universal memory in Membase.
- [How Membase Works](https://docs.membase.so/core-concepts/how-membase-works.md): How context flows into Membase's two knowledge stores (Memory and Wiki), gets structured, and comes back to your agents.
- [Chat in Dashboard](https://docs.membase.so/features/chat.md): Talk directly to your Membase knowledge base without going through an external agent. Chat with Memory answers questions using your stored memories and wiki documents, with citations and a linked graph panel.
- [Membase MCP](https://docs.membase.so/features/membase-mcp.md): Explore the MCP tools, resources, and prompts that power Membase agent integration. Learn how agents store, search, and retrieve memories via the Model Context Protocol.
- [Memory](https://docs.membase.so/features/memory.md): Explore and manage memories in Membase. Browse the knowledge graph and table view, filter by source and project, and understand how memories are created, updated, and deleted.
- [Knowledge Wiki](https://docs.membase.so/features/wiki.md): Store factual knowledge in Membase alongside your memories. Create wiki documents with markdown and [[wikilinks]], import Obsidian vaults, explore backlinks in a graph view, and let agents retrieve knowledge via the MCP wiki tools.
- [Bring Your Context Into Membase](https://docs.membase.so/getting-started/bring-context.md): Main ways to feed context into Membase: chat history import, agent conversations, Chat in Dashboard, app integrations, and Obsidian vault import.
- [Quickstart](https://docs.membase.so/getting-started/quickstart.md): Connect your first AI agent to Membase in 3 simple steps. Get persistent memory across sessions in under 5 minutes with one-click or CLI setup.
- [Use Your Context in Membase](https://docs.membase.so/getting-started/use-context.md): How to interact with your stored knowledge: Chat in Dashboard, agent retrieval across memory and wiki, and dashboard exploration for both stores.
- [Overview](https://docs.membase.so/index.md): Persistent, shared personal memory for your AI agents, so they keep important context across sessions.
- [Support & Troubleshooting](https://docs.membase.so/support/faqs.md): Get help with Membase. Chat with us from the dashboard, report bugs, suggest features, find troubleshooting tips, and connect with the Membase community on Discord.

## Optional

- [Changelog](https://docs.membase.so/changelog/index)
- [Community](https://discord.gg/vHgtDd6UTK)