Models

Models tell OpenVibely how to run AI work. Users configure them from the Models screen, then pick them as project defaults, task-specific choices, or agent defaults.

What Users Do In Models

Open Models from the System section of the sidebar and create a model config.

UI ConceptProduct Effect
ProviderChooses Anthropic, OpenAI, or Ollama.
Auth methodUses CLI auth, OAuth, API key, or local Ollama configuration depending on provider.
Model identifierSelects the provider model used for execution.
Default modelLets tasks run without choosing a model every time.
Reasoning, tokens, temperatureTunes model behavior where supported.
Max workersLimits how much concurrent work this model can run.
Worker timeoutPrevents stalled model executions from holding capacity forever.
Auto-start tasksAllows tasks created with the model to start immediately when configured.

Supported Providers

ProviderTypical Use
AnthropicHosted Claude models through CLI, OAuth, or API key auth.
OpenAIHosted OpenAI/Codex-compatible flows through CLI, OAuth, or API key auth.
OllamaLocal models through a local or configured Ollama base URL.

A test provider exists in source code for tests and is not documented as a normal production provider.

Choosing Defaults

Set an app-level default model if most work should use the same provider. Set a project default when a repository should prefer a different model. Pick a task model only when the task needs a one-off override.

PageWhy It Matters
QuickstartThe first task requires at least one usable model.
AgentsAgents can inherit or choose model behavior.
WorkersModel configs participate in capacity control.
Model ProvidersProvider-specific setup details live there.