Router Agent CLI - PraisonAI

The praisonai-ts CLI provides the router command for request routing analysis.

Quick Start

Simple Usage

# Analyze input and suggest routing
praisonai-ts router analyze "Help me debug this code"

# Get JSON output
praisonai-ts router analyze "What is 2+2?" --json

Example Output:

{
  "success": true,
  "data": {
    "input": "Help me debug this code",
    "selectedRoute": "code",
    "confidence": 0.95,
    "matchedRoutes": ["code", "question", "general"]
  }
}

Route Categories

The router analyzes input and suggests appropriate routing:

Route	Triggers
`code`	code, debug, function, programming
`math`	calculate, math, equation
`research`	research, find, search
`creative`	write, create, generate
`question`	what, how, why, explain
`greeting`	hello, hi, hey
`general`	Default fallback

SDK Usage

For programmatic routing:

import { RouterAgent, Agent } from 'praisonai';

const codeAgent = new Agent({ name: 'CodeExpert', instructions: '...' });
const mathAgent = new Agent({ name: 'MathExpert', instructions: '...' });

const router = new RouterAgent({
  routes: [
    { agent: codeAgent, condition: (input) => /code|debug/i.test(input) },
    { agent: mathAgent, condition: (input) => /math|calculate/i.test(input) }
  ]
});

const result = await router.route('Help me debug this');

For more details, see the Router Agent SDK documentation.

Router Agent SDK

Programmatic routing

Routing

Request routing

Router Agent

Image Agent

​Quick Start

​Route Categories

​SDK Usage

​Related

Router Agent SDK

Routing

Quick Start

Route Categories

SDK Usage

Related