> ## Documentation Index
> Fetch the complete documentation index at: https://agentrail.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# AgentRail: lifecycle API for coding agents

> AgentRail gives coding agents one compact API for the full development loop — issue intake, routing, PR submission, CI, review feedback, and shipping.

AgentRail is a local-first control plane for coding agents. It sits beside your agent (Claude Code, Codex, Cursor, or a custom harness) and provides a single source of truth for every stage of the development lifecycle: assigned work, PR state, CI results, review feedback, real-time events, and ship decisions. You install the CLI, run `agentrail init`, and your agents stop polling four different APIs.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="bolt" href="/docs/quickstart">
    Install the CLI and get AgentRail running in under five minutes.
  </Card>

  <Card title="Task Lifecycle" icon="arrows-spin" href="/docs/concepts/task-lifecycle">
    Understand how issues move from intake to shipped code.
  </Card>

  <Card title="SDK Reference" icon="code" href="/docs/sdk/overview">
    Use the TypeScript or Python SDK to integrate AgentRail into your harness.
  </Card>

  <Card title="API Reference" icon="rectangle-terminal" href="/docs/api/tasks/list">
    Explore every public endpoint with request and response examples.
  </Card>
</CardGroup>

## How it works

AgentRail normalizes provider issues (GitHub, Linear) into compact tasks, routes them to the right agent, and keeps track of every lifecycle transition so your agent never has to guess what to do next.

<Steps>
  <Step title="Install and initialize">
    Install the CLI with `npm install -g @agentrail-core/cli` and run `agentrail init` to create local config and your first agent profile.
  </Step>

  <Step title="Start the server">
    Run `agentrail server start` to bring up the local API and wake configured agents automatically.
  </Step>

  <Step title="Connect providers">
    Run `agentrail provider connect github` (or `circleci` / `linear`) to link your issue tracker and CI provider.
  </Step>

  <Step title="Verify with doctor">
    Run `agentrail doctor` to confirm the API is reachable, your agent credentials work, and assigned work is visible.
  </Step>
</Steps>

## Choose your path

<CardGroup cols={2}>
  <Card title="Claude Code / Codex / Cursor" icon="robot" href="/docs/integrations/claude-code">
    Copy-paste agent instructions for managed local runners.
  </Card>

  <Card title="Custom harness (TypeScript)" icon="npm" href="/docs/sdk/typescript/installation">
    Build an external harness or MCP server using the TypeScript SDK.
  </Card>

  <Card title="Custom harness (Python)" icon="python" href="/docs/sdk/python/installation">
    Build a workflow runner or internal service using the Python SDK.
  </Card>

  <Card title="Self-hosting" icon="server" href="/docs/self-hosting/overview">
    Run AgentRail on your own hardware or a VPS with Docker.
  </Card>
</CardGroup>
