@media (prefers-color-scheme: dark) {
    .md-header__logo img {
      content: url('../images/praisonai-logo-dark.png');
    }
  }
  
  @media (prefers-color-scheme: light) {
    .md-header__logo img {
      content: url('../images/praisonai-logo-light.png');
    }
  }

/* Essential mobile fixes */
@media screen and (max-width: 768px) {
  html, body {
    overflow-x: hidden;
    width: 100%;
    margin: 0;
    padding: 0;
  }

  /* Mintlify specific selectors */
  .mint-page,
  .mint-scrollbar {
    overflow-x: hidden;
    max-width: 100vw;
  }

  .docs-container {
    padding-left: 1rem;
    padding-right: 1rem;
    width: 100%;
    max-width: 100vw;
  }

  .container {
    width: 100%;
    padding-left: 1rem;
    padding-right: 1rem;
    margin: 0 auto;
  }

  table {
    display: block;
    max-width: 100%;
    overflow-x: auto;
    -webkit-overflow-scrolling: touch;
  }

  /* Fix for code blocks and pre elements */
  pre, code {
    max-width: 100%;
    overflow-x: auto;
    white-space: pre-wrap;
    word-wrap: break-word;
  }
}

AgentOps PraisonAI Monitoring

Dashboard

Guide for setting up and using AgentOps monitoring with PraisonAI, including installation and dashboard configuration

PraisonAI Documentation

PraisonAI is a production-ready Multi-AI Agents framework with self-reflection, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. By integrating PraisonAI Agents, AG2 (Formerly AutoGen), and CrewAI into a low-code solution, it streamlines the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.

Home

Praison AI

Welcome to PraisonAI - The Next Generation AI Agent Framework

Introduction

Set up PraisonAI in your development environment

Installation

Create AI Agents and make them work for you in just a few lines of code.

Quick Start

Agents

Tasks

Process

Learn how to create AI agents that can use tools to interact with external systems and perform actions.

Tools

AI Agents with Tools

Learn how to create AI agents with memory capabilities for maintaining context and information across tasks.

Memory

AI Agents with Memory

Learn how to create AI agents with custom knowledge bases

Knowledge

AI Agents with Knowledge

Agent-to-agent task delegation and collaboration

Handoff

Human-in-the-loop approval system for safety-critical operations in PraisonAI Agents

Approval

Human Approval System

LLM-based output validation and quality assurance for task outputs

Guardrails

Best practices for handling user input, validation, and safety in PraisonAI

Input Handling Patterns

Build stateful applications with persistent sessions in PraisonAI

Session Management

Learn how to create AI agents that can dynamically route tasks to specialized LLM instances.

Agentic Routing

Learn how to create AI agents that orchestrate and distribute tasks among specialized workers.

Orchestrator Worker

Agentic Orchestrator Worker

Learn how to create AI agents that can autonomously monitor, act, and adapt based on environment feedback.

Autonomous Workflow

Agentic Autonomous Workflow

Learn how to create AI agents that can execute tasks in parallel for improved performance.

Parallelization

Agentic Parallelization

Learn how to create AI agents with sequential prompt chaining for complex workflows.

Prompt Chaining

Agentic Prompt Chaining

Learn how to create AI agents that can generate and optimize solutions through iterative feedback.

Evaluator Optimizer

Agentic Evaluator Optimizer

Learn how to create AI agents that can efficiently handle repetitive tasks through automated loops.

Repetitive Agents

Use PraisonAI directly from your terminal with simple commands

Command Line Interface

AutoAgents automatically creates and manages AI agents and tasks based on high-level instructions.

AutoAgents

Generate high-quality images using PraisonAI Image Agents with both synchronous and asynchronous capabilities.

Image Generation

Image Generation AI Agents

Self-reflection enables agents to evaluate and improve their own responses before delivering them.

Self Reflection Agents

Self Reflection AI Agents

Learn how to create AI agents that can efficiently interact with vector databases for knowledge retrieval and storage.

RAG Agents

Learn how to create AI agents that can perform step-by-step reasoning and extract information

Reasoning Extract Agents

Learn how to create AI agents with advanced reasoning capabilities for complex problem-solving.

Reasoning Agents

Guide for creating and using multimodal AI agents in PraisonAI for processing images, videos, and other media types

Multimodal Agents

Learn how to use LangChain tools and utilities with PraisonAI agents.

LangChain Agents

Async AI Agents allow you to run AI tasks asynchronously, improving performance and efficiency in your applications.

Async Agents

Learn how to create simple yet powerful AI agents in just a few lines of code.

Mini AI Agents

Learn how to generate chain-of-thought reasoning data using PraisonAI Agents.

Generate Reasoning Data

Generate Synthetic Reasoning Data Agents

Learn how to create AI agents that can write and execute Python code safely using e2b code interpreter.

Code Agent

Code Execution AI Agent

Learn how to create AI agents that can perform complex mathematical calculations, unit conversions, and financial computations.

Math Agent

Math AI Agent

Learn how to create AI agents that return structured, type-safe outputs using Pydantic models and JSON.

Structured AI Agents

Build persistent, memory-aware agents with session management and complex workflows

Stateful Agents

Learn how to implement callbacks to monitor and log AI agent interactions, errors, and task completions.

Callbacks Agent

AI Agents with Callbacks

Learn how to create AI agents that can intelligently chat with PDF documents using vector databases for efficient information retrieval.

Chat with PDF

Chat with PDF Agents

How to integrate camera feeds with PraisonAI multimodal agents for real-time visual analysis

Camera Integration

Multi-tiered memory with quality scoring and graph support

Advanced Memory System

Advanced knowledge management system for AI agents

Knowledge Base

Stateful conversations and remote agent connectivity

Sessions & Remote Agents

Human-in-the-loop approval for dangerous operations

Approval System

Output validation and quality assurance for tasks

Learn how to implement agent-to-agent task delegation in PraisonAI

Agent Handoffs

Overview of supported language models in PraisonAI, including OpenAI, Groq, Google Gemini, Anthropic Claude, and configuration examples

Models in PraisonAI

Guide for integrating OpenAI's ChatGPT models with PraisonAI, including configuration for both single and multi-agent setups

OpenAI ChatGPT

Instructions for integrating Ollama's open-source language models with PraisonAI, including configuration and usage examples

Ollama

Guide for integrating Groq's high-performance language models with PraisonAI, including API setup and configuration

Groq

Instructions for integrating Google's Gemini models with PraisonAI, including API setup and configuration details

Google Gemini

Google Gemini Agents

Guide for integrating OpenRouter's unified API access to various language models with PraisonAI, including setup and configuration

OpenRouter

Instructions for integrating Anthropic's Claude models with PraisonAI, including API setup and agent configuration

Anthropic

Instructions for integrating AWS Bedrock models with PraisonAI, including API setup and agent configuration

AWS Bedrock

Guide for integrating Cohere's language models with PraisonAI, including API setup and configuration examples

Cohere

Guide for integrating Mistral AI's language models with PraisonAI, including API configuration and usage instructions

Mistral

Learn how to use Deepseek models with PraisonAI Agents for various applications.

DeepSeek Agents

Configuration examples for various other language models with PraisonAI, including Ollama, FastChat, LM Studio, and Mistral API

Other Models

Guide for integrating Firecrawl web scraping capabilities with PraisonAI, including custom tool implementation for web page content extraction

Firecrawl PraisonAI Integration

Guide for training and deploying models with PraisonAI, including Hugging Face and Ollama integration with detailed configuration options

PraisonAI Train

Interactive environment to test and run your AI Agents

Playground

Praison AI Agents Playground

Guide for using CrewAI framework with PraisonAI, including installation, setup, and execution of agent-based tasks

CrewAI with PraisonAI

Guide for using AG2 framework with PraisonAI, including installation, setup, and multi-agent conversation capabilities

AG2 with PraisonAI

Guide for using PraisonAI Agents framework, a lightweight package for creating and managing AI agents with advanced capabilities

PraisonAI Agents

Monitor and optimise performance with comprehensive latency tracking in PraisonAI

Latency Tracking

Instructions for running and writing tests for PraisonAI components, including unit tests and test automation

Test

Examples and templates for creating PraisonAI agent playbooks, from simple to detailed configurations with multiple roles and tasks

Agents Playbook

Guide for integrating the PraisonAI package into your Python projects, including YAML configuration and different execution modes

PraisonAI Package Integration

Guide for integrating external tools and APIs with PraisonAI, including examples of custom tool creation and implementation

Integrate with Tools

Guide for using PraisonAI in Google Colab environments, with example code and configurations for agent-based tasks

Google Colab Integration

Guide for implementing and using custom tools in PraisonAI with Google Colab, including examples of internet search and data processing tools

Google Colab Tools

Set up local development environment with Docker and live reload

Local Development

Get started with PraisonAI, an intelligent AI-powered tool

Quick start guide for PraisonAI with CrewAI, AG2 (Formerly AutoGen), and UI setup instructions

TL;DR

Guide for installing PraisonAI and its various components including framework support and additional features

Instructions for initializing PraisonAI with API keys and creating the initial agents configuration file

Initialise

Instructions for running PraisonAI from the command line, including framework selection and automatic mode

Guide to PraisonAI's automatic agent generation feature, supporting both CrewAI and AG2 frameworks for automated task execution

Auto Generation Mode

API Reference

Documentation for the praisonaiagents.agent.agent module

Agent Module

API reference for the agent handoff system

handoff

Documentation for the praisonaiagents.agents.agents module

Agents Module

Documentation for the praisonaiagents.agents.autoagents module

AutoAgents Module

Documentation for the praisonaiagents.task.task module

Task Module

Documentation for the praisonaiagents.process.process module

Process Module

Documentation for the praisonaiagents.handoff module - Enable agent-to-agent task delegation

Handoff Module

Documentation for the praisonaiagents.mcp module - Model Context Protocol integration

MCP Module

Documentation for the praisonaiagents.knowledge module - Advanced knowledge management and retrieval

Knowledge Module

Documentation for the praisonaiagents.memory module - Multi-tiered memory system with quality scoring

Memory Module

Documentation for the praisonaiagents.session module - Stateful applications and remote agents

Session Module

Overview of all available PraisonAI agents and their capabilities

Getting Started

Core Concepts

Workflows

Features

Models

Tools

Other Features

Monitoring

Developers

Getting Started (No Code)

API Reference

AgentOps PraisonAI Monitoring

AgentOps PraisonAI Monitoring

Dashboard

Getting Started

Core Concepts

Workflows

Features

Models

Tools

Other Features

Monitoring

Developers

Getting Started (No Code)

API Reference

​AgentOps PraisonAI Monitoring

​Dashboard

AgentOps PraisonAI Monitoring

Dashboard