GH Repository · basicmachines-co
basic-memory
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
- stars
- 3,964
- 30-day movement
- +5017/day
- Related entries
- 77
- Connections
- 6
python/uvmakedockerPythonprivacy-first-aiproductivityaimcpmcp-serverknowledge-managementopen-sourcellmpythonknowlege-graphobsidianobsidian-mdclaudemarkdownlocal-firstprivacy-first
basic-memory is an MCP server that gives AI conversations persistent memory, so you don't have to re-explain your project each session. It is a Python project with a local-first, markdown-based approach, integrating with Obsidian-style knowledge management and shipping Claude/MCP configuration files.
Reach for it when you want your AI assistant to retain project context across conversations without sending data to a third-party cloud.
Use it to
- Persist project context across AI chat sessions
- Serve a local markdown knowledge base to Claude via MCP
- Manage notes in Obsidian-compatible markdown files
- Run a privacy-first memory layer for LLM tools
- Deploy via Docker or Smithery
For Developers using Claude or MCP-compatible AI tools
- Role
- mcp-server
- Language
- Python
- Licence
- AGPL-3.0
- Forks
- 282
- Open issues
- 51
- Last push
- 2026-09-15
- Latest release
- v0.1.0 · 2025-02-07
- Skills shipped
- 15
topicsmcpknowledge-managementmarkdownlocal-firstprivacyclaude