March 14, 2026

The control plane for your agentic research.

Folio is a local file workspace for running deep analysis with AI agents. Label, summarize and extract structured from thousands of files using LLMs. Bring your own AI API keys. Keep your files private. Review results in a document-friendly UI, not a text-only terminal.

How it works

  1. Add your files to a Folio project
  2. Either connect Claude Code with a single command (npx skills add usefolio/folio) or use the built-in agent to give instructions.
  3. Tell your agent what you need: labels, extractions, summaries
  4. Approve operations in the sidebar before they touch your data
  5. Watch the results fill in row by row

The workspace shows all your operations in one place, with an interface that allows you to easily review results across thousands of files.

What you can do

Label - tag hundreds of documents by type, jurisdiction, relevance.

Extract - pull dates, clauses, figures, names into structured columns across your entire corpus.

Summarize - condense each document into a sentence, a paragraph, a verdict.

Ask - pose a question to every document in the set. Get per-document answers you can sort and filter.

Built for scale

Folio handles thousands of files.

Every job shows its progress: which documents are processing, which have completed, which have errored. Cost estimation before you run anything. Total spend visible in the menu bar.

The operational surface of a data pipeline, built for users who have never touched one.

You stay in control

The agent works in a sidebar. Every operation appears as a proposal: which files, which prompt, what it will cost. You approve, modify, or reject before anything runs.

Browse results, adjust prompts and point the agent in the right direction.

This is human-first by design. Not autonomous AI that disappears with your question and returns with an answer you can't verify.

Local and private

Your files are never stored remotely. Processing runs through your own AI accounts. Nothing tracked, nothing stored remotely.

No enterprise contract. No account creation.

The deeper idea

Backend data infrastructure is becoming a personal tool.

Knowledge workers now have access to more intelligence than they know what to do with. They need the same tools that technical teams used to direct that intelligence: pipelines, structured queries, batch operations. But those tools have to meet them where they are.

The agents need tools. The tools need to show their work.