Get up and running with Membase in under 5 minutes. By the end of this guide, your agent will have persistent memory across sessions.
Step 1: Create Your Account
Go to app.membase.so and create your account.
Membase is currently in private beta. You’ll need an invitation code to sign up. You can get one from an existing user, or join our Discord server and request an invitation code in the #invitation-code channel. Step 2: Connect Your Agent
From the dashboard, go to the Agents tab and click + Add Agent, then pick your client.
Most agents connect with a single command. A browser window opens automatically for authentication.
Cursor
ChatGPT
Claude Desktop
Claude Code
VS Code
Poke
Gemini CLI
OpenCode
OpenClaw
MCP URL
Click “Add to Cursor” in the dashboard. Cursor installs Membase automatically.
Go to Settings > Apps > Advanced Settings, click Create app, and enter the MCP URL:https://mcp.membase.so/mcp
npx -y membase@latest --client claude-desktop
npx -y membase@latest --client claude-code
Click “Add to VS Code” in the dashboard. VS Code installs Membase automatically.
Go to Integrations and add the MCP URL:https://mcp.membase.so/mcp
npx -y membase@latest --client gemini-cli
npx -y membase@latest --client opencode
openclaw plugins install @membase/openclaw-membase
For any MCP-compatible client, use the server URL directly:https://mcp.membase.so/mcp
For detailed step-by-step instructions for every client, see the Agents guide. Step 3: Start Using Memory
Once connected, your agent can read from and write to Membase. There are two core operations: saving memory and retrieving it.
Saving memory (add_memory)
Tell your agent something worth remembering. Your agent calls add_memory to store it in Membase.
I prefer TypeScript over JavaScript, and I use Bun as my package manager.
My current project is a Next.js app with Supabase for auth.
✓ Saves the conversation as an episode
✓ Extracts entities: TypeScript, Bun, Next.js, Supabase
✓ Links related entities and episodes in your knowledge graph
Retrieving memory (search_memory)
Next time you (or any connected agent) need context, your agent calls search_memory to pull relevant memories.
Set up a new project for me.
✓ Found: "Prefers TypeScript over JavaScript"
✓ Found: "Uses Bun as package manager"
✓ Found: "Current project uses Next.js + Supabase"
→ Agent sets up the project with TypeScript, Bun, and Next.js without you repeating anything.
You’re all set! Your agent now has persistent memory powered by Membase. Memories are automatically created, updated, and shared as you interact.
Next Steps
