Provider overview
How Cerevisor connects to models, provider types, the library, resolution order, and per-agent overrides.
The provider types
| Type | What it is | Authentication | Cost model |
|---|---|---|---|
| Anthropic | Direct API to Claude (Opus, Sonnet, Haiku). Cerevisor runs the agents itself. | API key. | Per token. |
| Gemini | Direct API to Google's Gemini models (2.5 / 3.x families). Cerevisor runs the agents itself. | API key from Google AI Studio. | Per token, with a >200K input-tier bump on Pro models. |
| Claude Agent SDK (shown as Claude Pro / Max — via Claude Code) | Claude Code's own engine, running inside Cerevisor. Nothing to install: Cerevisor carries its own copy and uses yours when yours is newer. Claude Code runs the work; Cerevisor supervises. | Anthropic API key (separate keychain slot from the Anthropic provider) or a Claude Pro/Max subscription. | Per token via your Anthropic account, or your Claude plan's quota (shown as $0). |
| OpenAI-compatible | Any endpoint speaking the OpenAI Chat Completions API. | API key (or none, for Ollama). | Per token, or free (local). |
| OpenAI Codex CLI (shown as ChatGPT Plus / Pro — via Codex) | OpenAI's Codex runs the work; Cerevisor supervises. Cerevisor installs the helper for you in one click. | Browser sign-in with your ChatGPT account (device code as fallback). | Subscription quota (shown as $0). |
| Cursor Agent | Cursor's agent. Cursor runs the work; Cerevisor supervises. | Cursor API key. | Per token, billed to your Cursor account. |
| Antigravity (shown as Google AI plan — via Antigravity) | Google's Antigravity runs the work; Cerevisor supervises. Multi-model: Gemini, Claude, and an open-weight model on one Google plan. | Browser sign-in with your Google account. Nothing to install by hand — Cerevisor installs the helper for you. | Your Google plan; Antigravity reports no usage counts, so Analytics shows no figure. |
Cerevisor also works with xAI's Grok Build, which runs the work in its own engine like Codex and Cursor do.
Anthropic, Gemini, Claude Agent SDK, Codex CLI, Cursor Agent, and Antigravity are singletons: one entry per type. OpenAI-compatible allows any number of entries, so you can have OpenAI + Ollama + OpenRouter side by side as separate library entries.
Who runs the agent. With Anthropic, Gemini, and OpenAI-compatible providers, Cerevisor runs the agents itself, so approving individual actions, steering an agent mid-run, attaching skills, and automatic retries when an output misses its definition all work. With Claude Agent SDK, Codex CLI, Cursor Agent, and Antigravity, the external tool runs the work in its own engine while Cerevisor supervises: you set the rules up front, and you trade those step-by-step Cerevisor features for that tool's own behavior, tool catalog, and (usually) subscription billing. Cerevisor shows you exactly this trade-off on the provider's capability card when you add it.
The Provider Library
All your credentials live in the Provider Library, accessed via Settings → Providers.
Each entry has:
- A name (auto-generated from type + base URL, editable).
- The provider type.
- Connection details (base URL, model defaults).
- A "default" badge: exactly one entry is the default at any time.
API keys are stored in the OS keychain. They're never written to a .cerevisor file and never logged.
Provider resolution
When an agent runs, Cerevisor decides which provider to use in this order:
- The agent's own provider, if you set one on the agent.
- The workflow's provider, if you set one for the workflow.
- The library default.
- The first provider that is switched on, if there is no default.
This means a workflow can run mixed providers (different agents use different providers) without you having to configure them per workflow.
The default
One library entry is always marked default. New workflows use it. Agents in those workflows inherit it unless you override.
Change the default in Settings → Providers → Set as default on the entry you want.
What background features use the default
Cerevisor has a few features that use the default provider quietly in the background:
- Chat builder: uses the default unless overridden in Settings → Chat Builder.
- Run retrospectives: at end-of-run, Cerevisor summarizes the run for memory storage. Uses the default.
- Meta-cognition enrichment: periodic summary of what Cerevisor has learned about you. Uses the default.
- Skill summaries: the richer descriptions of your skills shown in the Skills panel. Uses the default.
- Memory upkeep: a periodic tidy-up of your freeform memory entries.
These features run on your default even when the default is Codex, Cursor, Claude Code, or Antigravity: each call runs as one small agent task on that subscription, so a subscription-only setup keeps all background features working. If the default fails at runtime (not signed in, quota exhausted), Cerevisor automatically retries the call on another chat-capable credential in your library — no toggle to flip. Any spend from such a fallback is recorded and shows up in Analytics → Models, so you always know what a fallback cost.
Workflow execution vs. background features
The provider system is split into two paths:
| Path | Routing |
|---|---|
| Workflow execution | Decided per agent. Mixed providers OK. Every provider type OK. |
| Background features | The default first — including subscription providers — with automatic fallback to another chat-capable credential if the default fails. |
This is important because it lets you build a workflow where, say, every agent runs on Codex or Claude Agent SDK (billed to a subscription you already pay for) while background features quietly keep working too.
Where to go next
- Connect a provider: the per-provider setup walkthrough.
- Per-agent overrides: mixing providers within one workflow.
- Managing the Provider Library: library administration.