Connect a model provider

Cerevisor doesn't ship its own model. You connect it to a provider you already have access to. Seven kinds are supported, and you can have any number of each (except the singletons noted below).

If this is your first launch, the Provider Setup modal opens automatically. If you skipped it, open it any time from the title bar menu or via Settings → Providers → + Add provider.

This page walks through the simplest setup for each provider type. For the deeper guide, including managing multiple providers, per-agent overrides, and library administration, see Guides → Providers.

The seven provider types

Type	What it is	When to use it
Anthropic	Direct API connection to Claude (Opus, Sonnet, Haiku). Cerevisor runs the agents itself and asks you before anything risky.	You have an Anthropic API key and want the most capable hosted models with full Cerevisor control over every step. Singleton: one entry.
Gemini	Direct API connection to Google's Gemini (2.5 / 3.x families). Cerevisor runs the agents itself.	You have a Google AI Studio API key and want Gemini's long-context Pro models or its cheap Flash workhorses. Singleton. See the Gemini provider page for the dedicated walkthrough.
Claude Agent SDK	Anthropic's official Claude Agent SDK runtime running in-process. Claude Code runs the work in its own engine while Cerevisor supervises.	You want Claude Code-style agent execution (read/write/edit/bash/glob/grep tools out of the box) without leaving Cerevisor. Works with an API key or a Claude Pro/Max subscription. Singleton. See the Claude Agent SDK page.
OpenAI-compatible	Any endpoint that speaks the OpenAI Chat Completions API. Includes Ollama, OpenRouter, xAI, Together, Groq, Fireworks, vLLM, LM Studio, and OpenAI itself.	You want local models (Ollama), routing across providers (OpenRouter), or anything OpenAI-API-shaped. Multiple entries allowed.
OpenAI Codex CLI	Sidecar to OpenAI's official codex command-line tool. Codex runs the work in its own engine while Cerevisor supervises.	You have a ChatGPT subscription (Plus/Pro) and want to use Codex's quota rather than paying per token. Singleton.
Cursor Agent	In-process Cursor SDK runtime. Cursor runs the work in its own engine while Cerevisor supervises.	You have a Cursor account and want Cursor's agent (with its tool catalog and optional cloud execution). Singleton.
Antigravity	Sidecar to Google's Antigravity command-line tool (agy). Antigravity runs the work in its own engine while Cerevisor supervises.	You have a Google AI plan and want its quota to power the agents. Antigravity is multi-model: it runs Gemini, Claude, and an open-weight model on your Google plan, with no API key. Singleton.

Setting up Anthropic

You'll need an API key from console.anthropic.com.

1. In Provider Setup, click Anthropic.
2. Paste your API key.
3. Click Test connection. Cerevisor calls Anthropic's /v1/models endpoint to confirm the key works and to populate the model list.
4. Click Save.

The key is stored in your operating system's keychain, never in plain text on disk.

Setting up Ollama (local models)

You'll need Ollama installed and at least one model pulled (ollama pull llama3.1, for example).

1. In Provider Setup, click OpenAI-compatible.
2. Base URL: http://localhost:11434/v1
3. API key: leave blank, or enter any non-empty string: Ollama doesn't check.
4. Click Test connection.
5. Pick a default model from the dropdown.
6. Click Save.

You can repeat this with different base URLs to add OpenRouter, Groq, Together, or any other OpenAI-shaped endpoint as separate library entries.

Setting up OpenAI Codex CLI

You'll need Codex installed (npm install -g @openai/codex) and a ChatGPT Plus/Pro subscription.

1. In Provider Setup, click Codex CLI.
2. The wizard runs codex --version to confirm it's installed.
3. The wizard runs codex login status to check whether you're already signed in.
4. If you're not signed in, click Sign in. Cerevisor launches codex login, which opens your browser to complete sign-in with your ChatGPT account. If the browser flow doesn't work, choose use a code instead to get a URL + code you can enter manually. The wizard detects the completed sign-in automatically.
5. The wizard runs a smoke test (codex exec --json with a trivial prompt) to confirm everything works end-to-end.
6. Click Save.

Cerevisor never stores your OpenAI credentials, Codex owns its own authentication.

Windows note: Cerevisor automatically resolves the .cmd shim that npm install -g creates for the codex command. If the wizard reports "Codex not found" but codex --version works in your terminal, restart Cerevisor, PATH is read at launch.

Setting up Gemini

You'll need an API key from aistudio.google.com/apikey.

1. In Provider Setup, click Gemini.
2. Paste your API key.
3. Click Test connection. Cerevisor sends a tiny smoke-test request via the @google/genai SDK.
4. Click Save.

For the full walkthrough (model list, pricing quirks, thinking budgets), see the Gemini provider page.

Setting up Claude Agent SDK

You can sign in with an Anthropic API key from console.anthropic.com, or with a Claude Pro/Max subscription.

1. In Provider Setup, click Claude Code (Claude Agent SDK).
2. Pick a sign-in method with the toggle at the top: Anthropic API key (billed per token) or Claude subscription (uses your Pro/Max plan's quota).
3. In API-key mode, paste your key. (The key lives in a dedicated keychain slot, separate from the native Anthropic provider's slot, so you can configure both with the same key without conflict.) In subscription mode, paste a token from claude setup-token — or leave it blank to reuse an existing claude login on this machine.
4. Click Test connection.
5. Click Save.

For the current limitations (no per-tool prompts, no skill injection, etc.), see the Claude Agent SDK page.

Setting up Cursor Agent

You'll need a Cursor account with an API key generated at cursor.com/dashboard.

1. In Provider Setup, click Cursor Agent.
2. Cerevisor attempts to load the optional @cursor/sdk package. If it's not installed, you'll see an install hint.
3. Paste your Cursor API key.
4. Click Validate. Cerevisor calls Cursor's identity endpoint to confirm the key.
5. Click Run smoke test. Cerevisor spins up a trivial Cursor agent to confirm the local runtime works.
6. Click Save.

Cursor runs can also execute in the cloud, see Guides → Advanced → Cursor cloud runs for the full setup.

Setting up Antigravity

You'll need a Google account with an AI plan. The Antigravity CLI (agy) itself can be installed right from the setup panel — no terminal needed.

1. In Provider Setup, click Antigravity.
2. The wizard checks that the agy command is installed. If it isn't, click Install Antigravity CLI — Cerevisor runs Google's official install command for you, shows exactly what it runs, and streams the installer's output. It installs to your user folder, so no admin rights are needed. (Prefer your own terminal? The panel also shows the command and links to antigravity.google.)
3. If you're not signed in, click Sign in. Cerevisor launches agy login, which opens your browser to sign in with your Google account.
4. The wizard runs a quick verification to confirm a live session, then pick a default model. Antigravity is multi-model: the list includes Gemini Flash/Pro, Claude Sonnet/Opus, and an open-weight model, each at a chosen effort level.
5. Click Save.

Cerevisor never stores your Google tokens; Antigravity owns its own sign-in. One thing to know up front: Antigravity's output carries no usage counts, so Cerevisor can't show a cost figure for these runs — Analytics stays blank for them, which is expected.

Setting a default

When you have more than one provider in the library, one of them is marked as the default. New workflows use the default automatically; existing workflows keep whatever provider they were saved with.

To change the default: Settings → Providers, then click Set default on the entry you want.

Removing a provider

Settings → Providers, then click the trash icon on the entry you want to delete.

If any open workflow has an agent that references the credential you're trying to delete, Cerevisor blocks the deletion and shows you which agents would break. Either change those agents to a different provider first, or close the workflow.

Where to go next

→ Build and run your first workflow