> ## Documentation Index
> Fetch the complete documentation index at: https://ade-app.dev/docs/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, with your existing sign-in. It downloads its own copy of each agent the first time a machine needs it, so there is nothing to install. 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.

## The five agents

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

> [card] Claude Code
>
> Strong default for coding and project reasoning. API key or your Claude subscription sign-in.

> [card] Codex
>
> OpenAI's coding agent. ChatGPT sign-in or configured OpenAI access.

> [card] Cursor
>
> Cursor agent runs from inside ADE. Cursor API key or Cursor sign-in.

> [card] Factory Droid
>
> Factory's Droid agent, including AGI mode. Factory sign-in or API key.

> [card] OpenCode
>
> Local or OpenRouter-backed CLI workflows. OpenCode config and a provider key.

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

![Anthropic](https://mintcdn.com/ade-ac1c6011/lmMpn49wx_3bhn_c/media/logos/models/anthropic.svg?fit=max\&auto=format\&n=lmMpn49wx_3bhn_c\&q=85\&s=9961fc27cb76594234ea2b46281dff91)

![OpenAI](https://mintcdn.com/ade-ac1c6011/h8tcu_q5iZ_LGW1L/media/logos/models/openai.svg?fit=max\&auto=format\&n=h8tcu_q5iZ_LGW1L\&q=85\&s=53e6bae29a99cda478387e0a331e7a21)

![Gemini](https://mintcdn.com/ade-ac1c6011/lmMpn49wx_3bhn_c/media/logos/models/gemini-color.svg?fit=max\&auto=format\&n=lmMpn49wx_3bhn_c\&q=85\&s=a9da7bbd2f36258e6c193b2722420e3b)

![Qwen](https://mintcdn.com/ade-ac1c6011/h8tcu_q5iZ_LGW1L/media/logos/models/qwen-color.svg?fit=max\&auto=format\&n=h8tcu_q5iZ_LGW1L\&q=85\&s=351ee0ecc17dc337c8b7ccbc60d61000)

## Add and verify

**1. Choose the provider**

Pick the one you already use, or start with Claude Code if you're unsure.

**2. Add credentials**

Paste an API key, or sign in from the provider's page. A sign-in you already have in the provider's own CLI is reused.

**3. Verify**

Click **Verify** or **Refresh**. ADE checks the provider and confirms it can start sessions.

**4. Set a default model**

Choose a default model for chat. You can override it per session later.

> [!WARNING]
>
> Provider calls go from your machine straight to the provider. ADE does not proxy model requests through an ADE-hosted service.

## If verification fails

> [accordion] Troubleshoot a failed provider
>
> * Confirm the key is active and has model access.
> * If the provider reads "Downloading …", wait for it to finish; if it reads "Couldn't download …", choose **Retry download**.
> * Sign in again from the provider's page; the sign-in terminal runs ADE's copy of the agent.
> * Return to **Settings → AI Providers** and click **Refresh**.

## Next

> [card] [Open a project](https://ade-app.dev/docs/getting-started/open-project.md)
>
> Point ADE at the Git repository you want it to manage.

> [card] [AI providers](https://ade-app.dev/docs/configuration/ai-providers.md)
>
> Per-provider setup, models, and defaults in detail.


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