#60 · Primary category: Knowledge Base & RAG

basic-memory

ai claude knowledge-management knowlege-graph llm local-first markdown mcp obsidian obsidian-md open-source privacy-first privacy-first-ai productivity python

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

Project last updated:08/30/26

GitHub Stars

3.8K

Forks

268

Contributors

43

License

AGPL-3.0

Why we included this project

Basic Memory gives AI assistants a persistent place to store what they learn about your project. Notes live as plain Markdown files on your disk, so the knowledge base stays readable and portable, and a graph built from observations and wikilinks gives your assistant structured context instead of a growing conversation dump. Because it speaks the Model Context Protocol, it works across Claude, Codex, Cursor, ChatGPT, and other MCP-capable clients without vendor lock-in. Semantic search lets both you and your AI find notes by meaning, and the local-first design means a self-hosted, air-gapped setup is genuinely possible. People who want a memory layer they own instead of another opaque, vendor-hosted service will find the trade-offs laid out plainly, and the local version is free to evaluate before deciding whether the optional cloud tier is worth paying for.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category