Plain text in. A connected graph out.
Plain Markdown files, semantic connections, and a knowledge graph that grows with every conversation. Open source, local-first, works with any AI.
Open Source · 3K+ Stars · 57K Downloads/mo · Free to Start
Every conversation creates structured notes that persist across sessions. Your AI picks up exactly where you left off — decisions, preferences, project context, all there when you need it.
Notes connect through [[wiki-links]] and typed relations. Your AI understands how ideas relate to each other, finds patterns across your knowledge, and surfaces context you'd forgotten about.
One knowledge base, every AI tool. Claude, ChatGPT, Gemini, Cursor, VS Code, Codex, Obsidian — all connected through the Model Context Protocol. Your knowledge travels with you.
Everything is stored as plain Markdown files. Run locally on your machine, use the cloud, or sync between both. Open in any text editor, version with git, back up however you like. No lock-in.
Find notes by meaning, not just keywords. Ask for "that conversation about database scaling" and get results even if you never used those exact words.
Keep work, personal, and research knowledge separate. Each project has its own knowledge graph, its own context. Switch between them without mixing concerns.
Give your team a single, shared cloud workspace. Knowledge isn't confined to one person — anything a teammate writes is immediately available to everyone else and to their AI assistants. Edit a note together in real time, hand work off between humans and agents, and build one connected knowledge base instead of scattered copies.
Bring in your conversations from ChatGPT, Claude, and Gemini. Months of context, imported in minutes. Don't start from scratch.
Define structured note types — meetings, decisions, people, whatever fits your workflow. Validate notes against your own conventions and keep your knowledge consistent as it grows.
---title: Persontype: schemaentity: personversion: 1schema: name: string, full name role?: string, job title email?: string, contact email works_at?: Organization, employer expertise?(array, areas of knowledge): stringsettings: validation: warn frontmatter: tags?(array): string status?(enum): [active, inactive, archived]------title: Ada Lovelacetype: persontags: [mathematics, computing]status: active---# Ada Lovelace## Observations- [name] Ada Lovelace- [role] Mathematician and Writer- [expertise] Mathematics- [expertise] Computing theory## Relations- works_at [[Analytical Engine Project]]Basic Memory is AGPL-3.0 licensed. Inspect the code, run it yourself, contribute improvements. No black boxes, no proprietary formats, no surprises.
## Comparison
Most AI memory tools are black boxes. Basic Memory is the only one where your knowledge stays human-readable, editable, and yours.
| Feature | AI Native Memory | Other AI Memory | Basic Memory |
|---|---|---|---|
| You can read your AI's memory | |||
| You can edit your AI's memory | |||
| Works across LLMs | |||
| Multi-user shared knowledge | |||
| Local-first (your machine) | |||
| Open source | |||
| MCP native | |||
| Works with Obsidian / VS Code | |||
| Semantic knowledge graph |
## Get started
Try it for 7 days. Your notes stay yours either way — start building a knowledge base that grows with you.
Knowledge tools built to last
© 2026 Basic Memory - Basic Machines