> ## Documentation Index
> Fetch the complete documentation index at: https://ade-ac1c6011-ade-im-seeing-error-messag-eright-58df792e.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# ADE — Agentic Development Environment

> Orchestrate parallel AI coding agents from a unified desktop control plane. Lanes, worker runs, context packs, and conflict detection — all local-first.

<CardGroup cols={2}>
  <Card title="Get Started" icon="rocket" href="/welcome" color="#7C3AED">
    New to ADE? Start here. Learn what it does, install the app, and set up your first project in 5 minutes.
  </Card>

  <Card title="App Guide" icon="grid-2" href="/tools/project-home" color="#2563EB">
    Explore every tab — Run, Lanes, Chat, Files, Graph, PRs, Workers, CTO, and more.
  </Card>

  <Card title="Settings & Config" icon="gear" href="/configuration/settings" color="#059669">
    AI providers, integrations, permissions, budgets, and project configuration.
  </Card>

  <Card title="Changelog" icon="clock-rotate-left" href="/changelog" color="#D97706">
    What's new in ADE — latest features, improvements, and fixes.
  </Card>
</CardGroup>

***

## Why ADE?

AI coding agents are fast individually. Running them **in parallel** is where things break:

<CardGroup cols={2}>
  <Card title="Conflicts surface too late" icon="triangle-exclamation" color="#DC2626">
    Two agents edit the same files and you only find out at merge time.
  </Card>

  <Card title="Context resets every session" icon="rotate-left" color="#DC2626">
    Agents start cold instead of continuing informed from where they left off.
  </Card>

  <Card title="Oversight is fragmented" icon="puzzle-piece" color="#DC2626">
    Sessions, branches, costs, and artifacts live in separate tools with no unified view.
  </Card>

  <Card title="Execution is noisy" icon="volume-high" color="#DC2626">
    You can launch work but cannot track quality, ownership, or state across agents.
  </Card>
</CardGroup>

<Check>
  **ADE solves this** with isolated lanes, durable context packs, structured worker runs, a coordinator agent (CTO), and a workspace-wide view of branch state and merge risk.
</Check>

***

## Feature highlights

<AccordionGroup>
  <Accordion title="Lanes — Parallel workspaces" icon="code-branch">
    Isolated git worktrees, each with their own terminal sessions, agent context, and environment. Run agents in all of them simultaneously.

    [Explore Lanes →](/lanes/overview)
  </Accordion>

  <Accordion title="CTO — Always-on project agent" icon="crown">
    Delegates work to specialized workers, syncs with Linear, and manages budgets across all lanes.

    [Explore CTO →](/cto/overview)
  </Accordion>

  <Accordion title="Workers — Structured AI execution" icon="bullseye">
    Multi-step execution with planning, approval, validation, cost tracking, and full audit trails.

    [Explore Workers →](/cto/workers)
  </Accordion>

  <Accordion title="Automations — Background AI workers" icon="bolt">
    Trigger-driven rules that launch agent sessions or worker runs in response to git events, schedules, and webhooks.

    [Explore Automations →](/automations/overview)
  </Accordion>

  <Accordion title="Workspace Graph — Visual topology" icon="diagram-project">
    Infinite canvas showing every lane, branch, PR, and dependency. Run merge simulations visually and spot risks at a glance.

    [Explore Graph →](/tools/workspace-graph)
  </Accordion>

  <Accordion title="Proof — Intentional evidence capture" icon="camera">
    Agents capture screenshots, short recordings, and ingested browser traces through the `ade proof` CLI. ADE normalizes and routes each artifact to its worker run, chat session, PR, or Linear issue.

    [Explore Proof →](/computer-use/overview)
  </Accordion>
</AccordionGroup>