basicmachines-co /
basic-memory
Local Markdown notes your AI can read, write and search through MCP
- 4.3k stars
- Python
- Updated today
- Some experience
- Memory, RAG & data
AI chats usually forget everything when a session ends. Basic Memory fixes this by keeping notes as Markdown files in a folder (by default ~/basic-memory). Your AI client reads and writes those files through an MCP server, so the next conversation can pick up where the last one stopped.
Notes use observations and wikilinks, which build a knowledge graph over time. Search covers both keywords and meaning, using embeddings on SQLite or Postgres. Because the files are plain text, you can also open and edit them yourself. The README says Obsidian works on the same folder with no setup.
The core is free and local under AGPL-3.0. There is also a paid hosted cloud version with cross-device sync, mobile access and backups, plus a Teams option for shared workspaces. The README says the cloud is optional and you can export to plain Markdown at any time.
What it does
Markdown files as memory
Notes are plain text on your disk. You and your AI both write to the same files, and sync keeps them in step.
Knowledge graph
Observations and wikilinks inside notes link ideas together, so context builds up across conversations.
Semantic and hybrid search
Finds notes by meaning as well as keywords, using FastEmbed embeddings. Optional cross-encoder reranking is available.
Works with many MCP clients
The README gives setup snippets for Claude Desktop, Claude Code, Codex CLI, Cursor, VS Code and ChatGPT (via search and fetch tools).
Agent plugins and skills
The repo also ships a Claude Code plugin (session briefings, pre-compaction checkpoints, slash commands), shared SKILL.md files, and Hermes and OpenClaw plugins.
What you could build
- Keep a running log of project decisions that Claude or Codex can recall in later sessions.
- Ask your AI to find notes on a topic, such as JWT auth, by meaning instead of exact words.
- Browse and edit AI-written notes in Obsidian with the same wikilinks and graph view.
- Add session briefings and pre-compaction checkpoints to Claude Code with the plugin.
- Share one knowledge base across a team and its AI assistants using the cloud Teams option.
Get started
Install with uv (the --prerelease=allow flag is required), then add the MCP server to your AI client, for example with the Claude Code command above. Notes are saved in ~/basic-memory by default, and you can start by asking your AI to create a note about your project.
uv tool install basic-memory --prerelease=allowclaude mcp add basic-memory -- uvx --prerelease=allow basic-memory mcpCommands are copied from the project's README. Read it on GitHub for the full setup.
More in Memory, RAG & data
firecrawl
Web API that turns sites and search results into markdown or JSON for LLMs
markitdown
Python tool that turns PDFs, Office files, audio and more into Markdown for LLMs
graphify
Maps a codebase and its docs into a knowledge graph your AI assistant can query
claude-mem
Saves what your coding agent does and feeds the useful parts back into later sessions
vectorize-io/hindsight
Memory server that lets AI agents store, search and learn from past interactions
OpenViking
A context database that stores agent memory, docs and skills as browsable files
open-notebook
Self-hosted research notebook that chats with your documents using any AI provider
WeKnora
Self-hosted platform that turns documents into RAG search, an agent and a wiki
supermemory
Memory layer that lets AI assistants and apps remember users across conversations
gbrain
A shared memory for AI agents that stores sourced facts and answers with citations