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

# dotbot: Structured AI development for teams

> dotbot orchestrates Claude, Codex, and Antigravity through auditable workflow pipelines - every task isolated, every decision logged, every session resumable.

dotbot is a PowerShell-native framework that brings structure and accountability to AI-assisted software development. Rather than generating code in a black box, dotbot runs each task through a transparent, version-controlled pipeline where your team can see what was decided, why, and how to pick up where it left off. Every AI session, question, answer, and code change is tracked directly in your repository.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Install dotbot and run your first AI-assisted workflow in five steps.
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Install on Windows, macOS, or Linux via Homebrew, Scoop, or a source checkout.
  </Card>

  <Card title="Core Concepts" icon="book-open" href="/concepts/workflows-and-stacks">
    Understand workflows, stacks, task types, and the two-phase execution model.
  </Card>

  <Card title="CLI Reference" icon="terminal" href="/reference/commands">
    Full reference for every dotbot CLI command and flag.
  </Card>

  <Card title="MCP Server" icon="server" href="/mcp/overview">
    Connect Claude, Warp, and other AI tools to dotbot's 31-tool MCP server.
  </Card>

  <Card title="Dashboard" icon="gauge" href="/dashboard/overview">
    Monitor workflows, inspect audit trails, and manage settings from the web UI.
  </Card>
</CardGroup>

## What dotbot does

Most AI coding tools produce output without a record of how they got there. dotbot solves this by wrapping AI execution in a managed workflow engine where every task runs in isolation and every decision is captured.

<CardGroup cols={2}>
  <Card title="Workflow pipelines" icon="diagram-project">
    Define multi-step AI pipelines in `workflow.json` with tasks, dependencies, and form configuration.
  </Card>

  <Card title="Two-phase execution" icon="arrows-split-up-and-left">
    Analysis resolves ambiguity and builds context. Implementation writes code. No guesswork.
  </Card>

  <Card title="Git worktree isolation" icon="code-branch">
    Every task runs on its own branch. Parallel tasks never conflict.
  </Card>

  <Card title="Multi-provider AI" icon="robot">
    Switch between Claude, Codex, and Antigravity. Set models per task to control cost.
  </Card>

  <Card title="Enterprise registries" icon="building">
    Publish and share workflows across your organization via git-hosted registries.
  </Card>

  <Card title="Human-in-the-loop" icon="users">
    Route AI questions to stakeholders via Teams, Email, or Jira when input is needed.
  </Card>
</CardGroup>

## Get started in three steps

<Steps>
  <Step title="Install dotbot">
    Use a package manager, which installs a self-contained copy and puts `dotbot` on your PATH:

    ```powershell theme={null}
    brew install andresharpe/dotbot/dotbot     # macOS / Linux
    scoop bucket add dotbot https://github.com/andresharpe/scoop-dotbot
    scoop install dotbot                        # Windows
    ```

    Or install from a source checkout:

    ```powershell theme={null}
    git clone https://github.com/andresharpe/dotbot ~/dotbot
    pwsh ~/dotbot/bootstrap.ps1
    ```

    `bootstrap.ps1` drops a PATH shim into `~/.local/bin` (Linux/macOS) or `%LOCALAPPDATA%\Microsoft\WindowsApps` (Windows). Restart your terminal, then verify with `dotbot status`.
  </Step>

  <Step title="Initialize your project">
    Navigate to your project directory and run:

    ```powershell theme={null}
    dotbot init
    ```

    This creates a `.bot/` directory with the tracked `workspace/` tree and a `.gitignore`. The framework runtime is resolved from your active install, not copied into the project.
  </Step>

  <Step title="Launch the dashboard">
    Start the runtime and built-in web dashboard:

    ```powershell theme={null}
    dotbot go
    ```

    The dashboard opens at `http://localhost:8686`. From here you can run workflows, monitor tasks, and review session history. To start a workflow from the command line instead, run `dotbot run start-from-prompt`.
  </Step>
</Steps>

<Note>
  dotbot requires **PowerShell 7+**, **Git**, and at least one AI CLI - [Claude](https://docs.anthropic.com/en/docs/claude-cli), [Codex](https://github.com/openai/codex), or [Antigravity](https://antigravity.google/). No npm, pip, or Docker required.
</Note>