Skip to content
MCP server

OwlMem

Shared knowledge base, memory, tasks and vault for a team's AI agents

Install
Pricing
Freemium
Platforms
API, CLI, Web
Runs
Remotely
Version
0.94.2
Listing updated
2 days ago

About OwlMem

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

Every AI a team connects to OwlMem reads and writes the same store, so a decision recorded by one assistant is available to the next one. The server is hosted at mcp.owlmem.com and speaks streamable HTTP, with sign-in through OAuth 2.1 (PKCE and dynamic client registration) or a bearer token for scripts and CI.

Setup can be done three ways: paste the URL into a client that accepts remote MCP servers, ask an AI to read the setup guide and do it, or run npx -y owlmem install, which finds Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI and Claude Desktop on the machine, merges the entry into their configs and backs up each file it touches.

For agents that only run on demand, the docs describe a small polling approach: a cron job runs owlmem inbox --check every minute and starts the AI only when something is waiting. Agents can also report their usage to an endpoint so a team can see capacity.

The pricing page says vault items are encrypted on the user's devices, data is held on servers in Canada, and content is not used to train models.

Install

Run in a terminal

claude mcp add --transport http owlmem https://mcp.owlmem.com/mcp

Add to Settings → Connectors → Add custom connector

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

Add to ~/.cursor/mcp.json

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

Add to .vscode/mcp.json

{
  "servers": {
    "owlmem": {
      "type": "http",
      "url": "https://mcp.owlmem.com/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "owlmem": {
      "serverUrl": "https://mcp.owlmem.com/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "owlmem": {
      "type": "http",
      "url": "https://mcp.owlmem.com/mcp"
    }
  }
}

What it does

Shared knowledge base
One knowledge base and memory that every connected AI on the team reads and writes.
Tasks and inbox
Agents can pick up tasks and messages, with a CLI check that exits only when work is waiting.
Encrypted vault
Vault items are encrypted on the user's devices, so the vendor says it cannot read them.
One-command installer
`npx -y owlmem install` configures supported apps, backs up files and can be undone with --uninstall.
OAuth or token access
Approve in the browser with OAuth 2.1, or use a bearer token for scripts and older clients.
Per-agent control
Each connected AI appears in the console, where it can be switched off or deleted.

Good for

  • Give Claude, Cursor and Codex the same project background
  • Hand tasks between agents run by different teammates
  • Store API secrets for agents in an encrypted vault
  • Wake a cloud-hosted agent only when new work arrives
  • Record a repository's structure so the next AI already knows it

Pricing

Freemium

Pay per connected AI; first space is free with 2 AI agents; unlimited people on every plan

Prices change. Check owlmem.com before you buy.

OwlMem FAQ

Which clients can connect?

The docs give steps for Claude (web, desktop, mobile), Claude Code, Codex, ChatGPT, Cursor, VS Code with Copilot, Windsurf and Gemini CLI, plus any client that supports remote MCP with OAuth.

Do I have to sign in with OAuth?

No. A token created in the console can be sent as a bearer header, and clients that only run stdio servers can bridge through mcp-remote.

What happens when storage runs out?

Nothing is deleted. The AIs can still search and read, but new writes are refused until space is freed or the plan is upgraded.

Where is the data stored?

The pricing page says content, account and vault data are stored on servers operated in Canada.

Is OwlMem free?

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

How do I add OwlMem to Claude Code?

Run this command in your terminal: claude mcp add --transport http owlmem https://mcp.owlmem.com/mcp

What are the best alternatives to OwlMem?

The closest alternatives to OwlMem are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

Alternatives to OwlMem

  1. 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
  2. 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
  3. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  4. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  5. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity