Skip to main content
Settings is where you configure the infrastructure your agents depend on. Before creating your first agent, configure at least one model here. Think of Settings as the toolbox. Agents are built from the tools in the box. You define the tools once, and any agent in the workspace can use them.

​
The four settings sections

Models Registry

Register LLM providers and their API credentials. Every agent needs a model.

MCP Servers

Connect external tools — APIs, databases, and services agents can call.

Embeddings Models

Configure vector models for Knowledge Base (document RAG).

Sentinels

Define safety and pre-processing agents that intercept requests before your main agent runs.
  1. Models — required to create any agent
  2. Embeddings — required for Knowledge Base document RAG (long-term conversation memory is configured under the agent Memory step with Neuralyzer or CoD Summarizer, not here)
  3. MCP Servers — required if you want agents to use external tools
  4. Sentinels — optional, for safety and moderation workflows
All settings are scoped to the active workspace. If you switch to a different workspace, you’ll start with an empty settings configuration for that workspace.

​
Bootstrap from Docker Compose

Cloud models are not pre-filled from .env—add them in Settings → Models Registry. If you use the with-local-models profile and set OLLAMA_MODELS in .env, studio-init can register those Ollama models for you; still confirm they appear under Models and Embeddings before you create an agent.