Your files. A deeper you.
Give your AI your kind of context.
Connecting your computer to your LLM.
Your raw files are never uploaded to Locus. When your AI assistant searches, the matching excerpts go to that assistant, as they would if you pasted them in. How each mode works
We have tested it with cited answers in Claude Desktop, Claude Code and Cursor.
Your files, indexed
locally on your machine
What we have tested
No accuracy scores here yet: our early tests ran on one personal vault, too small to generalise from.
3
AI clients tested with cited answers: Claude Desktop, Claude Code and Cursor. The connect guide labels every other client by how far we have tested it.
Path + passage
on every search result, so your assistant can cite the exact file it used
macOS · Linux
where Locus runs today; Windows is not yet verified
How it works
Index your files locally
Point Locus at folders on your own machine. It parses, chunks, and embeds your files into a local vector index. Your raw files are never uploaded to Locus. The free local mode is optimized for English; managed mode uses a multilingual model.
Connect the AI assistants you use
Locus speaks MCP, the open standard for connecting tools to AI models. We have tested it with cited answers in Claude Desktop, Claude Code and Cursor. The connect guide has setup steps for more, each labelled with how far we have tested it. See the full list
Get cited answers
Ask a question that spans years of notes and documents. Your assistant answers it and points back to the exact files and passages it used.
Not sure which plan to start with?
Three quick questions point you at a starting plan.
A good starting plan for your answers
Starter $4/mo, billed yearly
The core engine is free and runs on your computer. Paid plans add managed embeddings — every plan is on the pricing page.
A simple illustrative scoring rule over your three answers — not measured Locus usage data or a cost model.
Get startedPricing
The core engine is free and runs on your own machine. Paid tiers add the hosted extras.
See pricing