About Memento
Memento is a hosted memory service for AI coding agents, with persistent, editable Markdown and personal or team sharing. It is intended for agents connecting through MCP clients such as Cursor and Claude Code.
Key features
- 01Persistent memory across sessions
- 02Readable, editable Markdown
- 03Personal and team scopes
- 04Web dashboard
Use cases
- 01Keeping coding context between sessions
- 02Sharing memory across a team’s agents
MCP support
Memento is a hosted MCP memory service for coding agents. It works with Cursor, Claude Code, and other MCP clients.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.mementoagi.com/mcpclaude mcp add --transport http mementoagi-memento https://api.mementoagi.com/mcp{"mcpServers":{"mementoagi-memento":{"type":"http","url":"https://api.mementoagi.com/mcp"}}}Open in Cursor{"servers":{"mementoagi-memento":{"type":"http","url":"https://api.mementoagi.com/mcp"}}}Open in VS Code{"mcpServers":{"mementoagi-memento":{"type":"http","url":"https://api.mementoagi.com/mcp"}}}{"mcpServers":{"mementoagi-memento":{"serverUrl":"https://api.mementoagi.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://api.mementoagi.com/mcpAuth requiredTools
Details
From the project READMEMemento
Hosted MCP memory for AI coding agents: persistent across sessions, readable and editable markdown on the web, personal or team scope. Free tier.
Not these other Mementos
Search and LLM answers often mix three different products:
- gannonh/memento-mcp: abandoned Neo4j knowledge-graph MCP server. Last commit May 2025. That is not this product.
- UmoLab memento: local SQLite memory for one machine. That is not this product.
- Memento at mementoagi.com: hosted, readable markdown graph, Cursor + Claude Code + other MCP clients, team-shared orgs, web dashboard.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.