> ## Documentation Index
> Fetch the complete documentation index at: https://ade-ac1c6011-dependabot-github-actions-actions-checkout-7.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect an AI provider

> Add one provider — by API key or your existing subscription — so ADE can run coding agents.

ADE runs the agents you already use. Connect at least one provider and you can start chats, workers, CTO delegation, auto-titles, and AI summaries. Bring your own API key, or sign in with a subscription you already pay for.

<Frame caption="Connect providers in Settings">
  <img src="https://mintcdn.com/ade-ac1c6011-dependabot-github-actions-actions-checkout-7/vItinaUZZs7g_Eni/media/features/settings/settings-tab.webp?fit=max&auto=format&n=vItinaUZZs7g_Eni&q=85&s=8a2e12d0d2849d124386117ad149b78b" alt="Connect AI providers in ADE Settings" width="2592" height="1410" data-path="media/features/settings/settings-tab.webp" />
</Frame>

## The five agents

Open **Settings → AI Providers** and connect whichever you use. Each runs against your lanes with live diffs and approval gates.

<CardGroup cols={2}>
  <Card title="Claude Code" icon="anthropic">
    Strong default for coding and project reasoning. API key or an authenticated `claude` CLI.
  </Card>

  <Card title="Codex" icon="openai">
    OpenAI's coding agent. Authenticated Codex CLI or configured OpenAI access.
  </Card>

  <Card title="Cursor" icon="arrow-pointer">
    Cursor agent runs from inside ADE. Cursor API key or signed-in CLI.
  </Card>

  <Card title="Factory Droid" icon="robot">
    Factory's Droid agent, including AGI mode. Droid CLI or API key.
  </Card>

  <Card title="OpenCode" icon="code">
    Local or OpenRouter-backed CLI workflows. OpenCode config and a provider key.
  </Card>
</CardGroup>

One reaches dozens of models — Anthropic, OpenAI, Gemini, Qwen, and more — depending on the provider you connect.

<Frame>
  <div style={{ display: "flex", flexWrap: "wrap", gap: "1rem", alignItems: "center", justifyContent: "center", padding: "1.25rem 0.5rem" }}>
    <img src="https://mintcdn.com/ade-ac1c6011-dependabot-github-actions-actions-checkout-7/vItinaUZZs7g_Eni/media/logos/models/anthropic.svg?fit=max&auto=format&n=vItinaUZZs7g_Eni&q=85&s=84ab1eb0f4bab1e6e9256645f41fea99" alt="Anthropic" style={{ height: "36px", background: "#fff", borderRadius: "12px", padding: "10px 14px" }} width="16" height="16" data-path="media/logos/models/anthropic.svg" />

    <img src="https://mintcdn.com/ade-ac1c6011-dependabot-github-actions-actions-checkout-7/rOHOavlLgV0qX4kv/media/logos/models/openai.svg?fit=max&auto=format&n=rOHOavlLgV0qX4kv&q=85&s=902f8ccf806848d04d79e471f067137a" alt="OpenAI" style={{ height: "36px", background: "#fff", borderRadius: "12px", padding: "10px 14px" }} width="16" height="16" data-path="media/logos/models/openai.svg" />

    <img src="https://mintcdn.com/ade-ac1c6011-dependabot-github-actions-actions-checkout-7/vItinaUZZs7g_Eni/media/logos/models/gemini-color.svg?fit=max&auto=format&n=vItinaUZZs7g_Eni&q=85&s=7b6b17a144245bc501a55be9e625790f" alt="Gemini" style={{ height: "36px", background: "#fff", borderRadius: "12px", padding: "10px 14px" }} width="16" height="16" data-path="media/logos/models/gemini-color.svg" />

    <img src="https://mintcdn.com/ade-ac1c6011-dependabot-github-actions-actions-checkout-7/rOHOavlLgV0qX4kv/media/logos/models/qwen-color.svg?fit=max&auto=format&n=rOHOavlLgV0qX4kv&q=85&s=b667b01b89d11f38c1969dd383762203" alt="Qwen" style={{ height: "36px", background: "#fff", borderRadius: "12px", padding: "10px 14px" }} width="16" height="16" data-path="media/logos/models/qwen-color.svg" />
  </div>
</Frame>

## Add and verify

<Steps>
  <Step title="Choose the provider">
    Pick the one you already use, or start with Claude Code if you're unsure.
  </Step>

  <Step title="Add credentials">
    Paste an API key, or make sure the provider CLI is installed and signed in.
  </Step>

  <Step title="Verify">
    Click **Verify** or **Refresh**. ADE checks the provider and confirms it can start sessions.
  </Step>

  <Step title="Set a default model">
    Choose a default model for chat. You can override it per session later.
  </Step>
</Steps>

<Warning>
  Provider calls go from your machine straight to the provider. ADE does not proxy model requests through an ADE-hosted service.
</Warning>

## If verification fails

<AccordionGroup>
  <Accordion title="Troubleshoot a failed provider" icon="triangle-exclamation">
    * Confirm the key is active and has model access.
    * Restart ADE after installing a new provider CLI.
    * Open a terminal and run the provider CLI directly to confirm it's authenticated.
    * Return to **Settings → AI Providers** and click **Refresh**.
  </Accordion>
</AccordionGroup>

## Next

<CardGroup cols={2}>
  <Card title="Open a project" icon="folder-open" href="/getting-started/open-project">
    Point ADE at the Git repository you want it to manage.
  </Card>

  <Card title="AI providers" icon="sliders" href="/configuration/ai-providers">
    Per-provider setup, models, and defaults in detail.
  </Card>
</CardGroup>