Skip to main content

Get config

Update config

Models

List chat and role models

Returns models grouped by provider.

List embedding models

Change embedding model

Changing the embedding model requires explicit confirmation, then rebuilds the semantic index for all active facts and readable wiki pages. Arden sends embeddings to the provider in batches.
Disable embeddings with JSON null. Full-text search remains available:
Follow rebuild progress:
Transient provider rate limits are retried using the provider’s reset time. While waiting, retry_at reports when the current batch will resume. Completed batches survive retries and server restarts. Retry a failed rebuild:

Add custom model

Register an OpenAI-compatible model endpoint:

Remove custom model

Providers

List providers

Returns all providers (Anthropic, OpenAI, OpenAI Codex, Google, OpenRouter, Custom) with connection status, available models, auth type, and masked API key hints.

Connect provider

OpenAI Codex uses browser OAuth instead of an API-key connect request:
Poll status while the browser flow is pending:

Disconnect provider

Services

External service credentials, including Exa, Telegram, and Slack tokens.

List services

Connect service

Disconnect service

Notifiers

Notifier configuration lives in the automation router. See Notifiers for /notifiers/* endpoints.

Directives

System directives customize the agent’s behavior. They persist across sessions and are injected into the system prompt.

Get directives

Update directives

Context

Get token usage

Compact context

Compress conversation history to free token space: