Skip to content
MCP server

Memmo

Shared, human-approved team memory for coding agents and pull request reviews

Install
Pricing
Freemium
Platforms
Web, API, self-hosted
Runs
Remotely
Version
0.9.5
Listing updated
2 days ago

About Memmo

Memmo is a freemium MCP server for knowledge and memory. It runs as a hosted remote server, so there is nothing to install locally.

Memmo collects what a team learns during AI coding sessions, such as risks, decisions and conventions, and holds it until a person approves it. Approved items are then delivered to agents like Claude Code, Codex and Cursor, and to pull request reviews, so a lesson learned by one teammate reaches everyone's agent.

The example entries on the site show the kind of memory it keeps: an idempotency-key rule after a duplicate-invoice outage, money stored in integer cents, or a warning not to upgrade a dependency because it breaks CI. Each is tagged by type and project and credited to the teammate who added it.

Plans are sized by retrievals (each time memory actually reaches an agent) and stored memories rather than seats, and the AI runs on your own model key, so you pay your provider directly for usage.

Install

Run in a terminal

claude mcp add --transport http memmo https://api.memmo.dev/mcp

Add to Settings → Connectors → Add custom connector

https://api.memmo.dev/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "memmo": {
      "url": "https://api.memmo.dev/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "memmo": {
      "type": "http",
      "url": "https://api.memmo.dev/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "memmo": {
      "serverUrl": "https://api.memmo.dev/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "memmo": {
      "type": "http",
      "url": "https://api.memmo.dev/mcp"
    }
  }
}

What it does

Reviewed memory
Items are approved by a person once before agents receive them.
Capture from sessions
Agent sessions add what they learn to one shared memory.
Served over MCP
Agents retrieve relevant memory through the remote MCP endpoint.
PR reviewer
A memory-grounded pull request reviewer on paid plans.
Audit log and export
Available on the Large team plan.
Self-host option
Enterprise can run in your own VPC with SSO.

Good for

  • Stop agents repeating a past mistake the team already hit
  • Give new teammates' agents the team's conventions
  • Ground pull request reviews in earlier decisions
  • Keep an audit trail of what agents were told

Pricing

Freemium

Free plan; Small team, Large team and Enterprise tiers (prices not shown)

Prices change. Check memmo.dev before you buy.

Memmo FAQ

Is there a free plan?

Yes: 500 retrievals a month, 250 stored memories and one project with two repos, with unlimited teammates.

Do I pay per seat?

No. Unlimited seats on every plan; plans differ by retrievals and stored memories.

Whose model key is used?

Your own, so you pay your model provider for AI usage.

Which agents does it serve?

Claude Code, Codex and Cursor are named, along with pull request reviews.

Is Memmo free?

Memmo has a free plan, with paid plans for more usage or features.

How do I add Memmo to Claude Code?

Run this command in your terminal: claude mcp add --transport http memmo https://api.memmo.dev/mcp

What are the best alternatives to Memmo?

The closest alternatives to Memmo are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Memmo

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools