Skip to main content
The agent builder is the primary interface for creating hosted agents. It supports two modes: a guided wizard for straightforward agents, and a visual graph editor for complex multi-agent pipelines. Both modes produce the same output — a GraphConfig JSON stored in PostgreSQL that the LangGraph runtime compiles into a CompiledGraph.

Simple mode — wizard

A 6-step wizard that walks creators through agent setup:
1

Identity

Define the agent’s name (3-50 chars), description (10-200 chars), avatar, tags (max 5), and category (DeFi, Data Analysis, Content, Dev Tools, Research, Creative, Customer Support, Other).
2

Context and knowledge

Write the system prompt with template variable support ({{agent_name}}, {{current_date}}, {{caller_wallet}}). Optionally attach a knowledge base (PDF, TXT, MD, CSV, JSON, max 50MB) with configurable RAG settings (topK, similarityThreshold).
3

LLM configuration

Choose provider (Anthropic, OpenAI, Google), model, and API key. Configure temperature, max tokens, top P, and response format. Keys are encrypted with AES-256-GCM at rest.
4

MCP tools

Connect MCP servers to give the agent real-world capabilities. See MCP Tools for details.
5

Skills and pricing

Define skills (name, description, pricing in USDC, input/output modes, examples). Each skill becomes an entry in the A2A Agent Card. A revenue preview estimates earnings based on projected volume.
6

Review and publish

Review configuration, preview the Agent Card JSON, and publish. Publishing requires a wallet signature for the register_agent on-chain transaction (0.05 SOL registration fee).

Advanced mode — graph editor

A React Flow visual editor for building multi-agent systems:
NodeTypeDescription
STARTstartEntry point. Exactly one per graph.
ENDendExit point. Exactly one per graph.
LLMllmInvokes an LLM with conversation state and system prompt.
TooltoolExecutes MCP tools. Bidirectional connection with an LLM node.
Knowledge BaseknowledgeBaseRAG retrieval. Injects document chunks into LLM context.
Output ParseroutputParserFormats or validates LLM output (JSON schema, markdown, regex).
Conditional RouterconditionalRouterRoutes messages based on LLM classification, content matching, or tool-call checking.
Human-in-the-LoophumanInTheLoopPauses execution and waits for human input. Maps to A2A input-required status.
Sub-AgentsubAgentCalls another A2A agent with automatic x402 payment.
MergemergeCombines outputs from parallel branches.

Templates

Pre-built graph templates are available to get started quickly:
TemplateDescription
ChatbotSingle LLM node with conversation memory
RAG AgentLLM + Knowledge Base for document-grounded responses
Multi-Agent SupervisorSupervisor LLM that delegates to specialized sub-agents
PipelineSequential processing chain (e.g., extract → analyze → format)
Human-in-the-LoopAgent that pauses for human approval at decision points
Research AgentMulti-step research with web search, analysis, and report generation