Krimto
@krimto-labs
Open-source memory for AI coding agents. Tell your agent to "remember" something in Cursor, Claude Code, Codex, or Gemini CLI, and Krimto saves it as a plain markdown file in a git repo you own — not rows in a vendor's database. Recall it later in a new chat, a different editor,
Overview
What is Krimto?
Krimto is an open-source memory system for AI coding agents that stores facts as plain markdown files in a git repository you own. It enforces a user→team→org hierarchy for scoping knowledge and syncs across editors and machines without any vendor database. It is licensed under Apache-2.0 and designed for solo developers and teams.
How to use Krimto?
Install Krimto with npx @krimto-labs/krimto init — the setup wizard detects your editor and enables automatic memory. In any supported editor (Claude Code, Cursor, Codex, Gemini CLI), tell your agent “remember X” to save a fact; later ask “what do you know about X?” to recall it. Run krimto notes in the terminal or krimto ui for a browser dashboard. For team memory, use npx @krimto-labs/krimto team init and share the join command with teammates.
Key features of Krimto
- Facts are plain markdown files in a git repo you control.
- User → team → org hierarchy governs who sees what.
- Cross-editor and cross-machine sync via one MCP server.
- Open source under Apache-2.0 license.
- SQLite + vector index for fast keyword and semantic recall.
- Self-hostable via
npxor Docker on any Node 20+ system.
Use cases of Krimto
- Solo developer: remember project context across multiple editors and machines.
- Team collaboration: share relevant team knowledge while keeping personal notes private.
- Compliance and audit: review every fact change through git history and pull requests.
- Self-hosted enterprise: run Krimto behind your own firewall without vendor lock‑in.
FAQ from Krimto
What runtime does Krimto require?
Krimto runs anywhere Node 20+ is available. You can also run it in Docker with docker run -d -p 8080:8080 -v ~/.krimto:/data ghcr.io/krimto-labs/krimto:latest.
Where does Krimto store its data?
All data lives in ~/.krimto — the same folder regardless of which project you are working in. Every fact is a markdown file inside a git repository at that path.
How does team mode work in Krimto?
Team mode creates a shared git remote or a shared Krimto server. Each teammate joins with a command like krimto join --server <url> --key <key>. Personal and team notes sync together, with the most specific scope winning at recall.
Can I use Krimto without creating an account?
Yes, solo mode requires no account. Run npx @krimto-labs/krimto init and you’re ready to go. An account is only needed for the optional hosted Krimto Cloud (planned for v1.0).
How do I connect Krimto to an MCP client manually?
Point any MCP client at Krimto over stdio using: claude mcp add krimto -- npx -y @krimto-labs/krimto or add the equivalent JSON configuration: { "mcpServers": { "krimto": { "command": "npx", "args": ["-y", "@krimto-labs/krimto"] } } }.
