143.dev docs

143 runs coding-agent work as a team workflow. A request becomes a visible session, the agent works in a sandbox, reviewers inspect the diff and preview, and GitHub stays the source of truth for review, CI, and merge rules.

Start with the shortest path to a reviewable change. Add repo configuration, previews, integrations, automation, and self-hosting only when those details become relevant.

Good first path

• Connect GitHub: give 143 access to the repositories it can work in.
• Start a session: choose a repo, branch, coding agent, and clear task.
• Review and ship: inspect the transcript, diff, validation output, preview, and PR before merging.

Build toward production use

• Repo config: define setup, validation, and preview behavior in .143/config.json.
• Preview environments: run live UI and full-stack previews from a session.
• Linear agent: assign or mention @143 in Linear and keep progress tied to the issue.
• Slack agent: mention @143, DM the bot, or start from Slack App Home and keep progress tied to the conversation.
• Autopilot: let eligible work run automatically behind visible gates.
• Coding-agent auth: configure user and organization credentials outside prompts and repo files.
• External API: start sessions and automations from internal systems using scoped service-account tokens.
• Self-hosting quickstart: bring up a production-shaped single-node instance.
• Production deployment checklist: verify a self-hosted deployment before sending real work to agents.

For AI agents

Agents should prefer the raw Markdown version of a page when ingesting these docs. Every public page is available as a normal docs URL and as a raw Markdown URL ending in .md.