s60yucca/mnemos

Overview

Mnemos is a Go-based MCP server that provides memory and knowledge graph capabilities for AI agents. It stores and retrieves structured information using a graph database, enabling persistent context across sessions.

Best for

Best for
Developers experimenting with persistent memory for MCP-based AI agents

Use cases

• Give an AI agent long-term memory across conversations
• Store and query structured knowledge as a graph
• Integrate persistent context into MCP-compatible tools

How to use

Install

npx -y @s60yucca/mnemos setup claude

Tools exposed

• MCP-native
• Auto-summarization
• mnemos_store
• mnemos_search
• mnemos_context
• mnemos_get
• mnemos_update
• mnemos_delete
• mnemos_relate
• mnemos_maintain
• mnemos_runtime
• short_term
• long_term

Tested with

Claude Desktop, Claude Code, Cursor, VS Code, ChatGPT

Notes

Mnemos is a Go-based MCP server that provides memory and knowledge graph capabilities for AI agents. It stores and retrieves structured information using a graph database, enabling persistent context across sessions.

9 stars on GitHub. Last updated 2026-05-19. Licensed MIT.

Use cases

• Give an AI agent long-term memory across conversations
• Store and query structured knowledge as a graph
• Integrate persistent context into MCP-compatible tools

Pros

• Lightweight Go implementation with minimal dependencies
• Graph-based storage enables rich relational queries
• Open source with a permissive license

Cons

• Very early stage with only 9 GitHub stars and limited community
• No documentation beyond the repository README
• Requires manual setup and integration effort

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.