The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Cairn listing page.
A local-first, open-source harness for organizing your files with an AI agent.
Point Claude Code, Codex, Cursor — any MCP client — at a folder, and your agent gains a full file-organization toolset: list, read, search, grep, edit, move, tag, import documents, and semantically retrieve. No account, no cloud, no UI required. Your files never leave your machine.
Then ask your agent to "organize this folder and tag everything" — it will, using tools that run locally over your own files.
A cairn is a stack of stones that marks a trail. This one keeps your files in order and shows the way through them.
If you use Claude Code, setup is one command — the only prerequisite is
uv, which provides uvx:
Reopen Claude Code and ask:
"Organize this folder and tag everything."
Cairn's tools run locally over your files — reads happen freely, and any move/rename/edit asks for confirmation first. The first run auto-downloads the package (~5s); no clone, no build, no account.
[!TIP] Point
--workspaceat a copy of some notes for your first run — Cairn can move, rename, and edit files.
Using Codex? Same one-command flow (then run /mcp in a session to confirm):
Using Cursor or another MCP client? Same package, JSON config:
~ is expanded by Cairn, so ~/Documents/notes works in the CLI and in config files alike.
Just want to poke at it, no agent?
The agent-harness ecosystem converged on a clear pattern: the model and the agent loop are commodities supplied by the client (Claude Code, Codex, OpenCode). The durable value is the tools and the local data. So Cairn ships tools, not an agent — the client provides the loop, the approval prompts (driven by our tool annotations), and the chat. Cairn is just the local file-organization toolset that snaps into whatever harness you already use.
Everything is a thin adapter over one standard-library core, so the faces can never drift.
In Claude Code / Codex / Cursor (primary):
The server exposes read-only tools (list, read, search, grep, retrieve) that the client runs freely, and destructive tools (move, delete, edit) that it confirms first — driven by MCP tool annotations, so you get approval prompts with no UI of ours.
As a CLI:
With the optional web UI:
.uni formatA .uni file is a small JSON document — { uuid, content: "<html>", metadata, tags } — with tags stored in the file. A workspace is just a directory: fully
portable, no external database. Source documents (docx/pdf/pptx/…) import into
editable .uni docs; the originals are kept by default.
<workspace>/.cairn/ and never leave your machine.Cairn is young. Rough direction, and where help is most welcome:
.cairn/views/*.md).Have a use case that doesn't fit? Open an issue or start a discussion.
Contributions of every size are welcome — see CONTRIBUTING.md
for the project layout, dev setup, and how to add a tool. Good first issues are
labeled good first issue.
MIT — see LICENSE.