protoA local, privacy-first AI agent for the terminal

Runs in your terminal against the models you choose — local, self-hosted, or any OpenAI-compatible, Anthropic, or Gemini endpoint. Your code and context stay yours.

Get Started

Browse Guides

GitHub

Tutorials

Step-by-step walkthroughs for learning proto from scratch — install, configure, and run your first agentic sessions.

Guides

Task-oriented how-tos — connecting models, writing sub-agents, using hooks, running headless or in CI, and more.

Reference

Exact, complete reference — every settings key, slash command, keyboard shortcut, tool signature, and the beads task tracker CLI.

Explanation

Conceptual docs on how proto's subsystems work and why they are designed the way they are.

Contributing

Architecture deep-dives, the development workflow, SDK guides, and examples for contributors and extension builders.