agentbreeder

No Code — Dashboard UI

Build and deploy agents with drag-and-drop. No YAML or code required.

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.

FrameworkBest for
LangGraphMulti-step agents with loops, human-in-the-loop, complex state
OpenAI AgentsSimple, fast agents with handoffs between specialists
Claude SDKReasoning-heavy tasks, extended thinking, document analysis
CrewAIRole-based teams of agents working toward a shared goal
Google ADKAgents that live in Google Workspace and use Gemini natively
CustomBring your own agent code — wrap any Python or TypeScript agent

Supported Deployment Targets

All deployment targets are available from the Deploy to dropdown. Connect your cloud account once in Settings — then deploy anywhere without manual credential configuration.

TargetWhat it runs onBest for
LocalDocker Compose on your machineDevelopment, testing
AWS App RunnerServerless containers on AWSLow-ops production, auto-scaling
AWS ECS FargateContainer orchestration on AWSHigh-traffic, VPC-controlled
GCP Cloud RunServerless containers on Google CloudGoogle Workspace integrations
Azure Container AppsServerless containers on AzureMicrosoft ecosystem teams
KubernetesEKS / GKE / AKS / self-hostedExisting K8s clusters, advanced networking
Claude ManagedAnthropic-managed runtimeZero 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:

FieldValue
Emailadmin@agentbreeder.local
Passwordplant

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:

FieldWhat to set
NameSlug-friendly name (e.g. support-agent)
FrameworkChoose from the 6 supported frameworks
ModelPrimary model + optional fallback
Tools / MCP ServersSearch and add MCP servers or built-in tools from the registry
Knowledge BasesOptional — attach RAG indexes for semantic or hybrid search
PromptsSelect a versioned system prompt from the registry, or write inline
GuardrailsOptional — PII detection, hallucination check, content filter
Deploy toTarget cloud and region
TeamAssigns 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

MCP Servers

The dashboard has a built-in MCP server registry. From the agent builder:

  1. Click Add Tool → Search MCP Servers
  2. Browse your org's registered MCP servers or auto-discover from your connected cloud
  3. Click Add — the server is wired in as a sidecar automatically on deploy

You can also run agentbreeder scan from the CLI to discover locally running MCP servers and publish them to the registry for the dashboard to find.


Multi-Agent Orchestration (Visual Canvas)

The dashboard includes a ReactFlow-based drag-and-drop canvas for building multi-agent pipelines — no code required.

To open the canvas:

  1. Click New Orchestration in the top-right corner
  2. Drag agents from the registry onto the canvas
  3. Draw connections between them to define the flow
  4. Set the orchestration strategy (router, sequential, parallel, supervisor)
  5. Click Deploy Orchestration

The canvas generates an orchestration.yaml behind the scenes. At any point, click View YAML to see it.


Human-in-the-Loop Approvals

For sensitive workflows, you can require a human to approve before an agent proceeds:

  1. Open the agent builder → Advanced → Approvals
  2. Enable Require HITL approval
  3. Set the approvers (team or individuals)

When the agent hits an approval step, it pauses and sends a notification. The approver sees the pending action in the dashboard and can approve or reject.


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:

  1. Click Export agent.yaml
  2. Run agentbreeder deploy agent.yaml from your terminal
  3. 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.

LocalApp RunnerECS FargateCloud RunContainer AppsKubernetesClaude 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

WhatWhere
Write YAML yourselfLow Code →
Use the Python or TypeScript SDKFull Code →
All agent.yaml fieldsagent.yaml Reference →
Deploy from the CLIQuickstart →
All CLI commandsCLI Reference →
Multi-agent orchestrationOrchestration SDK →

On this page