AI providers

Configure Claude, Codex, Cursor, OpenCode, and other providers for ADE agent sessions.

ADE can route chats, CTO work, and workers through multiple providers. Configure at least one provider before starting agent work.

Supported paths

Provider	Typical use
Claude / Claude Code	General coding, planning, review, and worker tasks.
Codex	OpenAI coding workflows and CLI-backed sessions.
Cursor	Cursor agent sessions through the Cursor SDK.
OpenCode	Local or provider-backed OpenCode workflows.
OpenRouter / local endpoints	Cost routing, experimentation, or local models.

Configure a provider

1. Open Settings -> AI Providers

   Choose the provider you want to use.

2. Add credentials or sign in

   Paste an API key, configure a local endpoint, or authenticate the provider CLI.

3. Verify

   Run the provider check and make sure ADE can start a session.

4. Choose defaults

   Set your default chat model and any role-specific overrides you need.

Permission presets

Providers expose different native permission models. ADE maps them into a small set of practical choices:

Preset style	Use it when
Plan / read-only	You want the agent to inspect and propose first.
Default / edit	You trust the lane and want normal coding flow.
Full access	You are in a trusted environment and want minimal prompts.
Custom	You want the provider’s own config to decide.

Cost control

Running several agents in parallel can spend quickly. Use cheaper models for routine follow-up and stronger models for planning, architecture, and hard debugging. Review usage from Settings -> Usage.

Provider calls go directly from your machine to the provider or local endpoint you configure. Keep keys out of committed files.