No Code — Dashboard UI

Build, configure, and deploy production agents entirely from the AgentBreeder dashboard. No YAML. No code. No DevOps knowledge required.

Who this is for: Product managers, analysts, business users, executives, and anyone who wants to ship agents without touching a terminal.

Supported Frameworks

Every framework works in the dashboard. Pick the one that fits your use case from a dropdown — AgentBreeder handles the runtime scaffolding automatically.

Framework	Best for
LangGraph	Multi-step agents with loops, human-in-the-loop, complex state
OpenAI Agents	Simple, fast agents with handoffs between specialists
Claude SDK	Reasoning-heavy tasks, extended thinking, document analysis
CrewAI	Role-based teams of agents working toward a shared goal
Google ADK	Agents that live in Google Workspace and use Gemini natively
Custom	Bring your own agent code — wrap any Python or TypeScript agent

Supported Deployment Targets

All deployment targets are available from the "Deploy to" dropdown. No cloud credentials to configure manually — connect your cloud account once in Settings, then deploy anywhere.

Target	What it runs on	Best for
Local	Docker Compose on your machine	Development, testing
AWS App Runner	Serverless containers on AWS	Low-ops production, auto-scaling
AWS ECS Fargate	Container orchestration on AWS	High-traffic, VPC-controlled
GCP Cloud Run	Serverless containers on Google Cloud	Google Workspace integrations
Azure Container Apps	Serverless containers on Azure	Microsoft ecosystem teams
Claude Managed	Anthropic-managed runtime	Zero infrastructure — Anthropic handles everything

Getting Started

1. Open the dashboard

http://localhost:3001        # local dev stack

Or log in to your org's hosted AgentBreeder instance.

Default local credentials:

Field	Value
Email	`admin@agentbreeder.local`
Password	`plant`

2. Create a new agent

Click New Agent in the top-right corner. The visual builder opens.

3. Configure in the form

The builder asks you for:

Field	What to set
Name	Slug-friendly name (e.g. `support-agent`)
Framework	Choose from the 6 supported frameworks
Model	Primary model + optional fallback
Tools	Search and add MCP servers or built-in tools from the registry
Knowledge Bases	Optional — attach RAG indexes
Prompts	Select a versioned system prompt from the registry, or write inline
Deploy to	Target cloud and region
Team	Assigns RBAC and cost attribution automatically

4. Deploy

Click Deploy Agent. The dashboard runs the 8-step pipeline and shows live progress:

✅  YAML parsed & validated
✅  RBAC check passed
✅  Dependencies resolved
✅  Container built
✅  Deployed
✅  Health check passed
✅  Registered in org registry
✅  Endpoint returned

If any step fails, the deploy rolls back automatically.

5. Your agent is live

The endpoint URL appears in the dashboard. You can immediately:

Chat with the agent from the playground tab
View logs in real time
Monitor costs per token, per day, per team
Share the endpoint URL with your team

Editing an Agent

Open an agent from the registry → click Edit → change any field → Redeploy.

Every redeploy is versioned. You can roll back to any previous version from the History tab.

Eject to Low Code (View the YAML)

At any point, click View YAML to see the agent.yaml that the dashboard generated. This is human-readable and version-controllable.

To take full ownership of the YAML:

Click Export agent.yaml
Run agentbreeder deploy agent.yaml from your terminal
You are now in Low Code mode — see Low Code →

The exported YAML is identical to what the dashboard used. Nothing is hidden.

Tier Mobility

No Code (Dashboard)
  └─▶  View YAML          → copy into your IDE → Low Code
  └─▶  agentbreeder eject → full SDK scaffold  → Full Code

You can always go deeper — you never lose what you built. See Full Code →.

All Frameworks × All Deployment Targets

Every combination works. This matrix applies to No Code, Low Code, and Full Code equally.

	Local	App Runner	ECS Fargate	Cloud Run	Container Apps	Claude Managed
LangGraph	✓	✓	✓	✓	✓	✓
OpenAI Agents	✓	✓	✓	✓	✓	✓
Claude SDK	✓	✓	✓	✓	✓	✓
CrewAI	✓	✓	✓	✓	✓	✓
Google ADK	✓	✓	✓	✓	✓	✓
Custom	✓	✓	✓	✓	✓	✓

Claude Managed note

When deploying to claude-managed, no container is built — Anthropic manages the runtime. The framework field is still required and controls how the agent logic is structured inside the managed environment.

Next Steps

What	Where
Write YAML yourself	Low Code →
Use the Python or TypeScript SDK	Full Code →
All `agent.yaml` fields	agent.yaml Reference →
Deploy from the CLI	Quickstart →
All CLI commands	CLI Reference →

No Code — Dashboard UI

On this page