TypeScript AI Agents Framework

A production-ready Multi AI Agents framework for TypeScript

PraisonAI is a production-ready Multi AI Agents framework for TypeScript, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code solution to streamline the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.

Supported runtimes: The TypeScript SDK runs in any JavaScript runtime — Node, Bun, Deno, browser bundles, Tauri, React Native, Cloudflare Workers. Pass the API key through the Agent config on runtimes that lack process.env. See Browser & Mobile Runtimes for the patterns.

TypeScript

Quick Start

1. Simple Usage

   npm

   npm install praisonai@latest
   

   As of v1.7.4, praisonai requires Node.js 18 or later (openai@4 needs Node 18+). Importing the package no longer requires OPENAI_API_KEY — the key is only checked when an OpenAI client is created, so Anthropic and Google users can import { Agent } from 'praisonai' without one.

   v-next (from PR #4416): praisonai-ts no longer runs dotenv.config() on import, and no longer reads process.env.LOGLEVEL at import. The package is safe to import in any JavaScript runtime (browser, Electron renderer, webview, React Native). If you relied on the automatic .env load, install dotenv yourself and call dotenv.config() at the top of your entrypoint — see JS Import Safety & Runtimes.

   Building for mobile or a webview (Tauri, Electron renderer, React Native, iOS/Android WebView)? Import from the praisonai/mobile entry:

   import { Agent } from 'praisonai/mobile';
   

   The package root is not webview-safe by design (it re-exports the CLI and MCP server). See Browser & Webview Runtimes.

2. With Configuration

   export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
   
3. Create File

   Create app.ts file

   Code Example

   Single Agent

   import { Agent } from 'praisonai';
   
   const agent = new Agent({ 
     instructions: `You are a creative writer who writes short stories with emojis.`,
     name: "StoryWriter"
   });
   
   agent.start("Write a story about a time traveler")
   
4. Run Script

   npx ts-node app.ts
   

Source & contributing: the TypeScript/JavaScript SDK is developed in MervinPraison/PraisonAI at src/praisonai-ts/. The praisonai-js repo is only the npm mirror — file issues and PRs against the main monorepo. See Contributing.

Usage Examples

Single Agent Example

Create and run a single agent to perform a specific task:

import { Agent } from 'praisonai';

// Single agent example - Science Explainer
const agent = new Agent({ 
  instructions: `You are a science expert who explains complex phenomena in simple terms.
Provide clear, accurate, and easy-to-understand explanations.`,
  name: "ScienceExplainer",
  verbose: true
});

agent.start("Why is the sky blue?")
  .then(response => {
    console.log('\nExplanation:');
    console.log(response);
  })
  .catch(error => {
    console.error('Error:', error);
  });

Multi-Agent Example

Create and run multiple agents working together:

import { Agent, AgentTeam } from 'praisonai';

// Create story agent
const storyAgent = new Agent({
  instructions: "You are a storyteller. Write a very short story (2-3 sentences) about a given topic.",
  name: "StoryAgent",
  verbose: true
});

// Create summary agent
const summaryAgent = new Agent({
  instructions: "You are an editor. Create a one-sentence summary of the given story.",
  name: "SummaryAgent",
  verbose: true
});

// Create and start agents
const agents = new AgentTeam({
  agents: [storyAgent, summaryAgent],
  tasks: [
    "Write a short story about a cat",
    "{previous_result}"  // This will be replaced with the story
  ],
  verbose: true
});

agents.start()
  .then(results => {
    console.log('\nStory:', results[0]);
    console.log('\nSummary:', results[1]);
  })
  .catch(error => console.error('Error:', error));

Task-Based Agent Example

Create agents with specific tasks and dependencies:

import { Agent, AgentTeam } from 'praisonai';

// Create recipe agent
const recipeAgent = new Agent({
  instructions: `You are a professional chef and nutritionist. Create 5 healthy food recipes that are both nutritious and delicious.
Each recipe should include:
1. Recipe name
2. List of ingredients with quantities
3. Step-by-step cooking instructions
4. Nutritional information
5. Health benefits

Format your response in markdown.`,
  name: "RecipeAgent",
  verbose: true
});

// Create blog agent
const blogAgent = new Agent({
  instructions: `You are a food and health blogger. Write an engaging blog post about the provided recipes.
The blog post should:
1. Have an engaging title
2. Include an introduction about healthy eating
3. Discuss each recipe and its unique health benefits
4. Include tips for meal planning and preparation
5. End with a conclusion encouraging healthy eating habits

Here are the recipes to write about:
{previous_result}

Format your response in markdown.`,
  name: "BlogAgent",
  verbose: true
});

// Create Agents instance with tasks
const agents = new AgentTeam({
  agents: [recipeAgent, blogAgent],
  tasks: [
    "Create 5 healthy and delicious recipes",
    "Write a blog post about the recipes"
  ],
  verbose: true
});

// Start the agents
agents.start()
  .then(results => {
    console.log('\nFinal Results:');
    console.log('\nRecipe Task Results:');
    console.log(results[0]);
    console.log('\nBlog Task Results:');
    console.log(results[1]);
  })
  .catch(error => {
    console.error('Error:', error);
  });

Running the Examples

1. Set Environment Variables

   export OPENAI_API_KEY='your-api-key'
   
2. Create Example File

   Create a new TypeScript file (e.g., app.ts) with any of the above examples.

3. Run the Example

   npx ts-node app.ts
   

Tool Calls Examples

Direct Function Tools

Create an agent with directly registered function tools:

import { Agent } from 'praisonai';

async function getWeather(location: string) {
  console.log(`Getting weather for ${location}...`);
  return `${Math.floor(Math.random() * 30)}°C`;
}

async function getTime(location: string) {
  console.log(`Getting time for ${location}...`);
  const now = new Date();
  return `${now.getHours()}:${now.getMinutes()}`;
}

const agent = new Agent({ 
  instructions: `You provide the current weather and time for requested locations.`,
  name: "DirectFunctionAgent",
  tools: [getWeather, getTime]
});

agent.start("What's the weather and time in Paris, France and Tokyo, Japan?");

Package Structure

PraisonAI ships two entry points from one package.

• praisonai — the full framework: agents, tools, MCP, CLI, and everything else. Import this in Node and server builds.
• praisonai/mobile — a webview-safe subpath export (~77 kB bundle). Import Agent and its types from here in phone, browser, or Tauri builds. See Mobile Entry for details.

Parity Notices

A few Python names resolve differently in the TypeScript SDK. Reach for the runtime entry point below.

Python name	In TypeScript	Use instead
LLM	Type only — no runtime constructor. new LLM() throws.	Configure the model on the agent: new Agent({ llm: 'gpt-4o' }).
Task	Workflow-step class ({ name, execute }).	Pass a plain task object or string to Team — see Tasks.
FunctionTool	Not user-constructible.	Wrap a function with tool(fn) — see Custom Tools.

Some Python methods on Agent, Team, and Session have no TypeScript counterpart yet. The pages below flag the gaps; the full list lives in the SDK parity baseline.

Related

TypeScript Async

TypeScript Async overview

Mobile Entry

Webview-safe bundle from praisonai/mobile

Agent

Agent overview

Browser & Mobile

Run in Tauri, React Native, browser, and edge runtimes