Models, Tools, & Agents

Unlike common LLM aggregators that only unify models, AiMo Network aggregates models, tools, and agents, allowing services to be composed and integrated in a highly flexible, agent-native manner.

Service Primitives

All services registered on AiMo Network fall into one of three primitives: models, tools, and agents, differentiated by their API standards.

A single service can implement multiple primitives simultaneously.

Models

Model services provide LLM inference capabilities through OpenAI-compatible chat/completion endpoints.

// Request
POST /v1/chat/completions
{
  "model": "gpt-4",
  "messages": [
    { "role": "user", "content": "Hello" }
  ]
}

// Response
{
  "id": "chatcmpl-123",
  "choices": [{
    "message": { "role": "assistant", "content": "Hi there!" }
  }]
}

Tools

Tool services expose functionality following the MCP (Model Context Protocol) standard via JSON-RPC 2.0.

// Discover available tools
{ "jsonrpc": "2.0", "id": 1, "method": "tools/list" }

// Response
{
  "jsonrpc": "2.0", "id": 1,
  "result": {
    "tools": [{
      "name": "get_price",
      "description": "Get token price",
      "inputSchema": {
        "type": "object",
        "properties": { "symbol": { "type": "string" } },
        "required": ["symbol"]
      }
    }]
  }
}

// Invoke a tool
{ "jsonrpc": "2.0", "id": 2, "method": "tools/call",
  "params": { "name": "get_price", "arguments": { "symbol": "ETH" } } }

// Response
{
  "jsonrpc": "2.0", "id": 2,
  "result": { "content": [{ "type": "text", "text": "ETH: $3,245.50" }] }
}

Agents

Agent services enable autonomous agent-to-agent communication following the A2A (Agent2Agent) standard via JSON-RPC 2.0 over HTTP.

// Agent Card (capability discovery at /.well-known/agent.json)
{
  "name": "TradingAgent",
  "description": "Executes crypto trades",
  "skills": [{ "id": "execute_trade", "name": "Execute Trade" }],
  "protocolVersion": "0.3"
}

// Send task to agent
POST /a2a
{
  "message": {
    "messageId": "msg-123",
    "role": "user",
    "parts": [{ "text": "Buy 1 ETH at market price" }]
  }
}

// Task response
{
  "id": "task-456",
  "status": { "state": "completed" },
  "artifacts": [{ "parts": [{ "text": "Purchased 1 ETH at $3,245.50" }] }]
}

Best Practices

A single service can expose different primitives depending on the use case. Choosing the appropriate primitive helps AI agents interact with AiMo Network more effectively.

Example: Crypto AI Trading Agent

Use Case	Recommended Primitive	Protocol
Backend for a frontend application	Model	Chat/Completion
Tool for other agents to invoke	Tool	MCP
Autonomous agent-to-agent interaction	Agent	A2A