Quickstart - Membase

How to Start
3-Step Guide
Step 1: Create Your Account
Step 2: Connect Your Agent
Step 3: Start Using Memory
Saving memory (add_memory)
Retrieving memory (search_memory)
Next Steps

Give your AI agent persistent memory in just a few minutes. Watch the video for a quick overview, or jump straight to the step-by-step guide below.

How to Start

Watch a quick walkthrough to see the full setup in action.

3-Step Guide

Follow these steps to connect your first AI agent to Membase.

Step 1: Create Your Account

Go to app.membase.so and create your account.

Membase sign-up page

Membase sign-up page

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.

Add agent dialog

Add agent dialog

Most agents connect with a single command. A browser window opens automatically for authentication.

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

Run this command in your terminal:

npx -y membase@latest --client claude-desktop

Run this command in your terminal:

npx -y membase@latest --client claude-code

Go to Integrations and add the MCP URL:

https://mcp.membase.so/mcp

Run this command in your terminal:

npx -y membase@latest --client gemini-cli

Run this command in your terminal:

npx -y membase@latest --client opencode

Run this command in your terminal:

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.

Your prompt

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.

add_memory

✓ 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.

Your prompt

Set up a new project for me.

search_memory → results

✓ 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 don’t need to trigger any of this manually. Your agent decides when to save and when to search. Just chat normally.

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

Bring Your Context

Import chat history, connect Gmail, Calendar, and Slack.

Use Your Context

Chat with Memory, agent retrieval, and dashboard exploration.

All Agents

Full setup guides for all supported clients.

Connect Apps

Enrich memory with Gmail, Calendar, Slack, and more.

Bring Your Context Into Membase