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

# Flowfield: Parallel AI Workers with Shared Task Feeds

> Flowfield coordinates AI coding agents locally: shared task feeds, parallel workers in isolated checkouts, and explicit approve-before-integrate review.

Flowfield is a local service that coordinates AI coding agents across parallel tasks, keeping every piece of a task's lifecycle — intent, activity, questions, answers, and results — together in one shared feed. You interact with it through a browser UI at `localhost:8765` and a CLI, while your AI coordinator plans work and workers implement agreed tasks in isolated Git checkouts. Nothing leaves your machine: Flowfield stores all data in `~/.flowfield/` and requires no cloud account.

<CardGroup cols={2}>
  <Card title="Introduction" icon="rocket" href="/introduction">
    Learn what Flowfield is, how it works, and who it's for.
  </Card>

  <Card title="Quick Start" icon="bolt" href="/quickstart">
    Install Flowfield, connect Codex, and run your first task in one walkthrough.
  </Card>

  <Card title="Core Concepts" icon="book-open" href="/concepts/overview">
    Understand tasks, feeds, the board, workers, and the review workflow.
  </Card>

  <Card title="Codex Integration" icon="plug" href="/integrations/codex">
    Connect your Codex coordinator to Flowfield via MCP.
  </Card>
</CardGroup>

## Get up and running

<Steps>
  <Step title="Install Flowfield">
    Install the `flowfield-core` package using `uv` with Python 3.12:

    ```sh theme={null}
    uv tool install --python 3.12 flowfield-core
    ```

    The package bundles the CLI, service, and browser UI — no separate frontend install is needed.
  </Step>

  <Step title="Start the service">
    Start the local service and open the browser UI:

    ```sh theme={null}
    flowfield serve
    ```

    Open [localhost:8765](http://127.0.0.1:8765) in your browser. Keep the terminal open; Ctrl-C stops the service.
  </Step>

  <Step title="Initialize your project">
    In a second terminal, change to your project directory and run the setup commands:

    ```sh theme={null}
    flowfield project init
    flowfield project guidance preview
    flowfield project guidance install
    flowfield integration connect codex
    ```

    Review the generated files (`.flowfield/config.toml` and `.agents/skills/flowfield-coordinator/SKILL.md`) and commit them before running workers.
  </Step>

  <Step title="Start a Codex conversation and run your first task">
    Open a fresh Codex conversation in your project directory. Describe a small change, ask your coordinator to capture the task in Flowfield, move it to **Up Next**, and click **Run Queue**. Monitor progress in the browser, answer any questions in the task feed, and approve the result when it reaches **In Review**.
  </Step>
</Steps>

## Why Flowfield

<CardGroup cols={3}>
  <Card title="Shared Task Feeds" icon="messages" href="/concepts/tasks-and-milestones">
    Intent, worker activity, questions, answers, and results live in one feed per task — nothing gets lost across tools or conversations.
  </Card>

  <Card title="Parallel Workers" icon="code-branch" href="/concepts/board-and-queue">
    Independent tasks run simultaneously in isolated Git checkouts. Dependent tasks wait automatically until prerequisites are complete.
  </Card>

  <Card title="Explicit Review" icon="check-double" href="/concepts/results-and-review">
    No code reaches your project without your approval. Inspect the diff, try the result in an independent copy, request changes, then approve and integrate.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.