Personal AI memory layer on your own computer. Read/write durable memory across MCP clients.
A personal AI memory layer that follows you across every AI you use.
Memoro is a lightweight Windows app that gives every AI assistant you talk to (Claude, ChatGPT, Grok, Perplexity, Gemini) a shared, persistent memory of you: your projects, decisions, preferences, and the people in your life. Tell one AI something once; every other AI you use can pick it up from exactly where you left off.
Every AI chat starts from zero. Explain your project to Claude on Monday, switch to ChatGPT on Tuesday, and you're re-explaining everything. Memoro fixes that, without asking you to trust a third-party server with your data.
Memoro runs quietly in the background on your own computer. A small MCP (Model Context Protocol) connector, added once to each AI platform, lets your AI read and write to your memory. Memory is stored as "status cards": one focused, up-to-date summary per topic, not a raw chat log. An optional, free Cloudflare Worker and D1 layer, deployed in your own Cloudflare account, gives you access from anywhere, even when your computer is off.
Nothing is ever stored on a server we run. We don't operate one. Your data lives on your machine and, optionally, in cloud infrastructure you own.
Works with Claude, ChatGPT, Grok, Perplexity, and Gemini. Right click "Save to Memoro" browser extension for one off notes. Multi device sync via your own OneDrive or Google Drive (Pro). Team Projects: a shared memory for a team, with conflict resolution and an approval step for critical changes (Pro). Seven day free trial of every Pro feature, no card required.
Windows only for now (Mac and Linux planned). Download MemoroSetup.exe — free tier: unlimited local storage, one device, no account or card required. See the release notes for Pro pricing.
No hosting of your data, no data sales, no ads. The only thing Memoro sells is the software itself.
Early stage, actively developed. Issues and feedback welcome.
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
npx -y @memoro/mcp-serverMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-circassian1977-byte-memoro": {
"command": "npx",
"args": [
"-y",
"@memoro/mcp-server"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup reference@memoro/mcp-servernpmio.github.circassian1977-byte/memoro works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.