🦞 AI Agents That Work For You, 24/7

Self-improving multi-agent teams that solve complex tasks, automate workflows, and deliver to Telegram, Discord, Slack — with low-code simplicity.

Get Started

Build your first AI agent in minutes. Install, configure, and run.

Explore SDK

Agents, Tools, Workflows, Memory, Knowledge, and RAG capabilities.

Deploy

Docker, Cloud, MCP Server, A2A Protocol, and production patterns.

Quick Start

One‑line install — includes guided onboarding for Telegram, Discord, Slack, WhatsApp and the Claw dashboard.

macOS / Linux / WSL2

bash

curl -fsSL https://praison.ai/install.sh | bash

Isolated install via uv tool → pipx → venv fallback. CLI available at ~/.local/bin/praisonai.

Windows (PowerShell)

powershell

iwr -useb https://praison.ai/install.ps1 | iex

uvx (zero-install)

bash

uvx praisonai "2+2"

Runs PraisonAI without a permanent install. Requires uv.

pipx

bash

pipx install praisonai

Isolated persistent install. Requires pipx.

pip

bash

pip install "praisonai[all]"
praisonai onboard

Agent

python

from praisonaiagents import Agent

agent = Agent(instructions="You are a helpful AI assistant")
agent.start("Write a movie script about a robot on Mars")

🦞 AgentClaw

bash

pip install "praisonai[claw]"
praisonai claw

Open http://localhost:8082 — full UI with chat, agents, memory, knowledge, and channels for Telegram, Discord, Slack.

AgentTeam

python

from praisonaiagents import Agent, AgentTeam

researcher = Agent(name="Researcher", instructions="Research topics thoroughly")
writer = Agent(name="Writer", instructions="Write engaging content")

team = AgentTeam(agents=[researcher, writer])
team.start("Create a blog post about AI agents")

AgentFlow

python

from praisonaiagents import Agent, AgentFlow

researcher = Agent(name="Researcher", instructions="Research topics")
writer = Agent(name="Writer", instructions="Write content")

workflow = AgentFlow(steps=[researcher, writer])
workflow.start("Create a blog post about AI agents")

AgentOS

python

from praisonai import AgentOS
from praisonaiagents import Agent

# Deploy as web API
app = AgentOS(
    agents=[Agent(instructions="You are a helpful assistant")]
)
app.serve(port=8080)

Dashboard

Works With Every AI Provider

100+ LLM providers supported out of the box

Use Cases

AI agents solving real-world problems across industries

Research & Analysis

Conduct deep research, gather information, and generate insights from multiple sources automatically.

Code Generation

Write, debug, and refactor code with AI agents that understand your codebase and requirements.

Content Creation

Generate blog posts, documentation, marketing copy, and technical writing with multi-agent teams.

Data Pipelines

Extract, transform, and analyze data from APIs, databases, and web sources automatically.

Customer Support

Deploy 24/7 support bots on Telegram, Discord, Slack with memory and knowledge-backed responses.

Workflow Automation

Automate multi-step business processes with agents that hand off tasks, verify results, and self-correct.

Why PraisonAI?

Runs Anywhere

Your machine, cloud, or edge. Self-hosted with full control over your data.

100+ LLM Models

OpenAI, Anthropic, Google, Ollama, Groq — seamlessly switch between any provider.

Memory & Knowledge

Persistent memory, RAG knowledge bases, and context-aware conversations.

Self-Reflection

Agents that evaluate and improve their own responses for higher accuracy.

140+ Built-in Tools

Web search, file operations, databases, APIs — all ready to use out of the box.

Multi-Agent Workflows

Sequential, parallel, hierarchical orchestration with autonomous coordination.

Install

Python

bash

pip install praisonaiagents
export OPENAI_API_KEY=your_key

python

from praisonaiagents import Agent

agent = Agent(instructions="You are a helpful AI assistant")
agent.start("Write a movie script about a robot on Mars")

JavaScript

bash

npm install praisonai
export OPENAI_API_KEY=your_key

javascript

const { Agent } = require('praisonai');
const agent = new Agent({ instructions: 'You are a helpful AI assistant' });
agent.start('Write a movie script about a robot on Mars');

No Code

bash

pip install praisonai
export OPENAI_API_KEY=your_key
praisonai "Summarize the latest AI news"

Low Code

bash

pip install praisonai
export OPENAI_API_KEY=your_key

agents.yaml

agents:
  researcher:
    instructions: Research about AI trends
  writer:
    instructions: Write a blog post about the findings

bash

praisonai agents.yaml

The same --continue, --session, --output, and permission flags documented for praisonai run also work here — praisonai agents.yaml --continue --output json resumes the last session and emits machine-parseable output.

Explore

Agents

Single agents, multi-agent teams, coordination

Tools

Built-in tools, custom tools, MCP integration

Workflows

Multi-step pipelines, routing, loops

Memory & RAG

Vector stores, knowledge bases, retrieval

🦞 AgentClaw

Full UI with chat, agents, Telegram, Discord, Slack

Recipes

55+ production-ready AI tools

Platform Integrations

Slack

Deploy AI bots to Slack workspaces

Discord

Create Discord bots with agent intelligence

Telegram

Build Telegram bots in minutes

WhatsApp

Connect via WhatsApp Business

GitHub

Automate repos, issues, and PRs

Google

Calendar, Sheets, Drive, Gmail

Notion

Read and write Notion pages

Jira

Manage Jira issues and projects

CLI Commands

Full-featured CLI for deploying and managing AI agents

🦞 AgentClaw

bash

pip install "praisonai[claw]"
praisonai claw

# Custom port
praisonai claw --port 9000

# Add channels from the UI — Telegram, Discord, Slack, WhatsApp

Messaging Bots

bash

# Start a Telegram bot
praisonai bot telegram --token $TELEGRAM_BOT_TOKEN

# Slack with full capabilities
praisonai bot slack --token $SLACK_BOT_TOKEN --app-token $SLACK_APP_TOKEN \
  --agent agents.yaml --browser --web --memory --model gpt-4o

# Discord with custom tools
praisonai bot discord --token $DISCORD_BOT_TOKEN \
  --tools DuckDuckGoTool WikipediaTool

Browser Control

bash

praisonai browser navigate https://example.com
praisonai browser run "Click the submit button"
praisonai browser screenshot --output page.png
praisonai browser doctor

Skills & Plugins

bash

praisonai skills list
praisonai skills check --verbose
praisonai plugins list --enabled
praisonai plugins doctor

Sandbox

bash

praisonai "Run code" --sandbox strict
praisonai sandbox status
praisonai sandbox explain --agent work

🦞 AgentClaw

Full UI with bots and agents

Bot CLI

Deploy messaging bots

Browser CLI

Browser automation

Plugins CLI

Plugin management

Join the Community

Connect with developers building with PraisonAI

GitHub YouTube X LinkedIn