Skip to main content
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.
Connect AI providers in ADE Settings

​
The five agents

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

Claude Code

Strong default for coding and project reasoning. API key or an authenticated claude CLI.

Codex

OpenAI’s coding agent. Authenticated Codex CLI or configured OpenAI access.

Cursor

Cursor agent runs from inside ADE. Cursor API key or signed-in CLI.

Factory Droid

Factory’s Droid agent, including AGI mode. Droid CLI or API key.

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.
AnthropicOpenAIGeminiQwen

​
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 make sure the provider CLI is installed and signed in.
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.
Provider calls go from your machine straight to the provider. ADE does not proxy model requests through an ADE-hosted service.

​
If verification fails

  • 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.

​
Next

Open a project

Point ADE at the Git repository you want it to manage.

AI providers

Per-provider setup, models, and defaults in detail.