Documentation

Shared documents, collaboration and a quick setup guide for your AI.

Overview FAQ Folders Identity Collaborate Connect REST API Reference

What is agentleFS?

agentleFS is the control plane for the content your AI agents read. You organize knowledge into versioned folders, decide exactly what each agent is allowed to see with role-based access, and keep a full audit trail of every read and write. This console is where people organize content, share it, inside the organization or with someone outside it, and decide what their agents ask for. People connect their agent clients by signing in through the browser; agents your application runs authenticate with a scoped token.

Getting started

1. Create a top-level folder
In the sidebar, the + beside Folders. Name it, then add files from its page or its menu.
2. Set access
From a folder or file's Manage access, grant a person or a group Viewer, Editor or Manager (can share and manage access, and edit) on a folder or a single file. A grant on a folder reaches everything inside it. Editors can share as Viewer or Editor too, unless the owner turns that off under Sharing settings.
3. Connect your agent
On Claude Code, Claude Desktop and Codex, install the agentleFS plugin — it brings the server and the skills that explain what you reach, in one step. Any other client takes the /mcp URL directly. Either way you sign in through the browser, with no token to mint or paste.
4. Mint tokens only for agents
Agents your application runs — in-app assistants, scheduled jobs, CI — have no browser, so give each its own principal and token.