Manage adapters and models

This guide shows you how to connect model providers and choose what an agent runs on.

Everything here lives on one page: Settings → Server → Model providers. The sub-sidebar entry reads “Model providers”; the page heading reads “Adapters”.

What an adapter is

An adapter is the runner that executes an agent turn. There are two and the list is fixed — you cannot add a third.

Adapter	CLI	Transport
Control Center (built-in)	none	In-process agent loop, talks to providers over HTTP
Claude Code	claude	claude -p --output-format stream-json

Cursor, Codex, Anthropic, OpenAI and the rest are providers on the built-in adapter, not separate CLIs. What you can add is another provider — any OpenAI- or Anthropic-compatible endpoint. That is the next section.

Detection probes the server, not your machine

The Detected runners card lists what cc_server found on the server host’s PATH. On a thin or web client that is a different machine from the one you are looking at. Install the CLI on the machine that runs cc_server.

Connect a model provider

The built-in adapter needs at least one connected provider before it can run. Fourteen ship in the catalogue.

1. Go to Settings → Server → Model providers
2. Scroll to Providers & models
3. Find your provider and connect it:

Provider	How to connect
Anthropic	API key. A Claude Pro/Max subscription is not an Anthropic API login — use the Claude Code adapter for that plan
OpenAI, Codex, Cursor	Browser OAuth login, or an API key. Codex is ChatGPT Plus/Pro via the Codex Responses backend, not a CLI spawn
Kimi Code	Browser OAuth only — a device-code flow. It is a flat-rate plan, so it has no per-token price
OpenRouter, Groq, Google Gemini, DeepSeek, Mistral, xAI, z.ai, z.ai GLM Coding Plan, Moonshot (Kimi API)	API key

Checkpoint: the row’s badge changes to connected and expanding it lists the models that provider serves, each with its price per million tokens and context window.

OAuth tokens land in the server’s own credential store and are refreshed before they expire. Provider credentials are host-global — they are shared by every workspace on the install, not scoped to one.

Add a custom provider

Use this for Ollama, LM Studio, vLLM, or a private deployment.

1. In Providers & models, under Custom providers, press Add provider
2. Fill in a name, pick the API type (OpenAI-compatible or Anthropic-compatible) and give the base URL (for example http://localhost:11434/v1)
3. Add an API key if the endpoint needs one, then press Add provider

A custom provider appears in the same list, with a delete button its built-in siblings do not have.

Pick a model for an agent

1. Go to Settings → Workspace → Agents and select the agent
2. On the Settings tab, choose the adapter
3. Choose the model from the dropdown beside it

For the built-in adapter the dropdown is assembled live from every connected provider’s own catalogue. A provider with no stored credential contributes zero models, which is why an empty dropdown almost always means “nothing connected yet” rather than “nothing available”.

models.dev is enrichment, never a source of ids

The bundled models.dev catalogue supplies price and context window for a model that is already in the live list. It never adds a model id. If a model you expect is missing, the provider’s endpoint is not returning it.

Model ids for the built-in adapter are qualified provider/model and may carry a |-separated fallback chain. Under a fallback, cost is priced against the model that actually served the turn, not the one you asked for.

An agent with no adapter runs on the built-in loop

Every workspace seeds five agents — a CEO plus qa, architect, engineer and librarian — with no adapter and no model. Dispatch falls back to Control Center (built-in), not to the Default runners setting on this page, which is a client preference the dispatch path never reads. The run log records cc-harness for those runs, so the transcript names what actually ran.

With no model either, the built-in loop asks Anthropic for its default model. An agent left entirely unset therefore runs if you have connected an Anthropic account, and otherwise fails with No credential for provider "anthropic".

Finishing onboarding’s adapter step back-patches every agent that is still missing an adapter or a model — CEO and specialists, across every workspace that exists at that moment — with the pair you picked. Workspaces created later still seed all five unset. Set the adapter and model explicitly on every agent you intend to use.

Install a runner CLI

The built-in adapter needs no installation. For Claude Code, install its CLI on the server host with that tool’s own package manager, for example:

npm install -g @anthropic-ai/claude-code

Then press Refresh at the top of the page. Each detected row shows the resolved version and path, plus chips for whether it supports JSON mode and model selection.

An external CLI keeps its own credentials, in its own configuration, on the server host. Control Center does not manage them.

Adapter Arguments and Environment variables stay on this device

Each adapter row offers an Arguments field and an Environment variables dialog. Those values are stored on your device. The server reads launch argv and env from its own settings store. Put provider keys on the server (OAuth or the key field on the Model providers page), not in those two fields.

Restrict which providers a workspace may use

Provider governance is per workspace and is evaluated last-match-wins.

1. In Providers & models, flip the allow switch on a provider row off

That writes a deny statement for that provider in the active workspace and its models drop out of the catalogue for that workspace. Turning the switch back on removes the statement.

Troubleshooting

A runner shows as not found

• Check the CLI is on the server host’s PATH, not just yours
• A GUI-launched desktop app spawns its server with a minimal PATH; a CLI installed under a shell-only path may be invisible to it
• Press Refresh after installing

The model dropdown is empty

• The adapter is the built-in one and no provider is connected — connect one in Providers & models
• Or the provider is connected but denied by this workspace’s governance switch

A model runs but the price shows as unknown

The live model list carries the id; price and context come from models.dev. A brand-new model, or one from a custom provider, has no catalogue entry yet.

Related guides

• Create and configure an agent
• Manage API keys
• Diagnose an agent
• Manage costs

Related concepts

• The agent model
• Agent dispatch lifecycle