Skip to main content
Every agent has its own filesystem — a cloud-based storage space where Goose can read, write, and organize files.

​
How it works

Your agent’s filesystem is stored in the cloud and accessible from the chat interface. You can browse files in the sidebar, upload new ones, and view file contents inline. When Goose runs workflows, it can create and modify files directly. For example, if you ask Goose to research a company, it might save a report as a file in your workspace.

​
What you can do

  • Upload files — Drag and drop files into your workspace for Goose to reference.
  • Browse files — Use the file tree in the right sidebar to navigate your workspace.
  • View files — Click any file to preview it alongside your chat.
  • Create and organize — Create new files and directories to keep your workspace tidy.
  • Share files — Generate public links to share specific files with others.

​
Supported file types

Goose can work with a wide range of files:
  • Documents (text, markdown)
  • Code files (with syntax highlighting)
  • Images
  • Structured data (CSV, JSON)
  • Generated artifacts (HTML reports, slide decks, etc.)

​
Persistence

Files persist across chat sessions. Anything saved to your workspace today is available the next time you chat — or the next time an automation runs. This makes your workspace a growing knowledge base over time.

​
Shared files

Your organization also has a shared file space. Files placed in the shared directory are accessible across all agents in your organization.

​
Access from your coding agent

Prefer managing files from Claude Code, Cursor, or Codex? The GooseWorks MCP server exposes the same storage as MCP tools: read_file, write_file, list_directory, search_files, and more. Register it by pasting the install prompt into your agent: Paste this into your agent — Claude Code, Cursor, Codex, or a chat app like Claude or ChatGPT:
Your agent reads that page and follows it. It asks you before it installs anything, then runs the GooseWorks CLI with --all (it sets up every coding agent on your machine at once), opens a browser for Google sign-in, checks the install, and carries on in the same chat: it sets up your brand there (it asks for your website and a couple of quick questions), then gets back to what you asked for. You don’t need to reopen your agent; the GooseWorks tools also show up in its next session. If your agent is a chat app like claude.ai, the Claude desktop app’s chat or ChatGPT, it gives you the MCP connector address instead. The page only ever runs npx gooseworks@latest …. It writes your agent’s skills folder, your agent’s MCP config (for Cursor that is the global Cursor MCP config, plus the project’s .cursor/mcp.json if the folder has one), and ~/.gooseworks/credentials.json. The MCP config entries contain your sign-in token. It writes no other files. Installing is free; some skills spend credits when they run. The check at the end also reports whether ffmpeg and a browser are present; those only matter for rendering video ads on your machine and do not block the install. See MCP Servers → GooseWorks MCP for the full tool list and endpoint details.