Pi

Pi is an extensible AI agent that works from your terminal. Give it a goal and a working folder, and it can inspect files, run commands, edit content, and work through multi-step tasks.

Use Pi for software development, research notes, writing projects, data files, or hobby work. You can use Pi as is, prompt it to adapt itself to your workflow, or build other applications powered by Pi using the SDK.

New to Pi? Follow the Quickstart to install Pi, connect a model, and complete your first task.

If Pi is already installed, choose what you want to do:

• Use Pi interactively to add files, run commands, direct ongoing work, and export results.
• Choose a model or connect a subscription, API key, local model, or compatible endpoint.
• Continue or branch a session to resume work or explore another approach without losing history.
• Configure Pi for your preferences, working folders, instructions, and reusable resources.
• Understand how Pi works, including tools, context, sessions, and the agent loop.

Pi can reuse prompts, load specialized instructions, add executable integrations, change its terminal interface, connect model services, and distribute these resources as packages. Use the Quickstart customization chooser to select the smallest mechanism that meets your need.

• Use print mode for one-off and scripted tasks.
• Use JSON event stream mode to consume structured events from one run.
• Use RPC mode to control a separate Pi process.
• Use the TypeScript SDK to run Pi inside an application.

Use the reference pages to look up CLI options, settings, provider authentication, keybindings, and environment variables.

For platform-specific help, see Terminal Setup, Windows, tmux, Termux on Android, or Containerization.

Pi's tools and extensions run with the permissions of the Pi process. Project trust controls which project resources Pi loads, but it does not sandbox tool calls. Review Security before using untrusted files, repositories, extensions, or unattended automation.