Guides

Task-oriented how-tos for specific goals. Pick the guide that matches what you want to do.

Models & Auth

• Configure Models & Auth — Connect OpenAI-compatible, Anthropic, and Gemini endpoints

Agentic Features

• Use Sub-Agents — Spawn specialized agents to parallelize work
• Use Agent Teams — Orchestrate multi-agent pipelines
• Use Skills — Package reusable instructions as installable skills
• Use Hooks — Run shell commands on agent lifecycle events
• Connect via MCP — Attach external tools via the Model Context Protocol
• Language Server Protocol — Give the agent live diagnostics and go-to-definition
• Sandboxing — Isolate agent execution in a container
• Run Headless — Drive proto non-interactively from scripts and CI
• Schedule Prompts — Run prompts on a cron schedule

Workflow

• Approval Mode — Control which tools run automatically vs. require confirmation
• Manage Memory — Persist context across sessions
• Ignore Files — Exclude paths from the agent’s file access
• Trusted Folders — Pre-approve tool use for specific directories
• Export Sessions — Save and replay conversation history
• Token Caching — Reduce cost with prompt caching
• Agent Arena — Run multiple agents head-to-head for evaluation

IDEs & CI

• Visual Studio Code
• Zed
• JetBrains IDEs
• GitHub Actions

Customisation

• Themes — Change the terminal UI color scheme
• Language (i18n) — Run proto in a different language