Overview

Build and orchestrate Agents, Teams, and Workflows on a live canvas with AgentOS Studio.

Concepts

Agents: Build an agent by giving it a model, tools, and instructions. Add knowledge and memory to ground its responses and remember context. Teams: Build a multi-agent team that works toward a shared goal. Choose how the leader coordinates with members using coordinate, route, broadcast, or tasks mode. Workflows: Orchestrate agents and teams into step-based pipelines. Control the flow with loops, conditions, routers, and parallel execution. Use functions or CEL expressions to evaluate conditions and selectors. Registry: Register the components Studio composes with: tools, models, databases, schemas, knowledge, memory managers, and session summary managers. Register existing agents and teams to reuse them as members in Studio teams or steps in Studio workflows.

How It Works

Studio connects to your running AgentOS instance and uses a Registry to populate available components. Build visually, test interactively, and publish when ready.

Register your tools, models, databases, and schemas in a Registry
Pass the registry and a database to AgentOS
Open Studio in the AgentOS Control Plane to start building

from agno.os import AgentOS
from agno.db.postgres import PostgresDb
from agno.registry import Registry
from agno.models.openai import OpenAIChat
from agno.tools.websearch import WebSearchTools

db = PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai")

registry = Registry(
    name="My Registry",
    tools=[WebSearchTools()],
    models=[OpenAIChat(id="gpt-5-mini")],
    dbs=[db],
)

agent_os = AgentOS(
    id="my-app",
    db=db,  # Studio requires db to save and load agents, teams, and workflows
    registry=registry,
)

app = agent_os.get_app()

Development Lifecycle

Studio manages the full development lifecycle: build, test, publish, and version your agents, teams, and workflows.

1. Build

Create your agent, team, or workflow using the visual builder. Use tools, models, and knowledge bases from the Registry. Add instructions and configure the settings.

2. Save Draft or Publish Directly

Save your work as a draft or publish directly. Drafts can be edited and updated. Drafts help you test your component before publishing it.
Publish or draft multiple versions to checkpoint your progress.

3. Test

Once saved, test your draft or published version in the AgentOS UI:

Chat Page:
- Interact with your agent, team, or workflow in real time
- Run a specific version of the component by selecting it in the dropdown
View Traces: Inspect tool calls, model responses, and reasoning for each run
Debug Mode: Enable verbose logging to troubleshoot issues

Before publishing, test and make sure your agent handles edge cases and unexpected inputs gracefully.

4. Manage Versions

Access the full version history for any agent, team, or workflow: Two actions are available on this page:

Restore: open a draft for editing in Studio.
Set Current: choose which published version the API serves.

Drafts are mutable: you can edit them in Studio and delete them. Published versions are immutable and undeletable. To change a published version, publish a new one. Only published versions can be set as current.

Use descriptive version labels like v1.2-improved-instructions or before-refactor to make it easy to identify versions later.

Next Steps

Task	Guide
Build an agent	Studio Agents
Create a workflow	Studio Workflows
Compose a team	Studio Teams
Set up the registry	Studio Registry
Browse component APIs	Components API reference

Get Started

AgentOS

Example Usage

Concepts

How It Works