Installation

Set up PraisonAI in your development environment

Install PraisonAI, set one provider key, and run an Agent in your own app.

Fastest start — one line, no Python knowledge needed:

bash

curl -fsSL https://raw.githubusercontent.com/MervinPraison/PraisonAI/main/install.sh | sh

python

from praisonaiagents import Agent

agent = Agent(instructions="Be helpful")
agent.start("Summarise the top AI news today")

Bot (gateway + channels)

pip install "praisonai-bot[gateway,bot]"

Full (wrapper)

pip install praisonai

Code (runtime)

pip install praisonai-code

Train (fine-tune)

pip install "praisonai-train[llm]"

Browser (Chrome automation)

pip install "praisonai-browser[all]"

Agents (SDK)

pip install praisonaiagents

npm

npm install praisonai

One-Liner

curl -fsSL https://raw.githubusercontent.com/MervinPraison/PraisonAI/main/install.sh | sh

Terminal-only (smaller)

pip install praisonai-code — agentic CLI without gateway or bots

Bots + gateway only

pip install "praisonai-bot[gateway,bot]" — channel runtime without the wrapper

Full (default)

pip install praisonai — wrapper, code, bot, and SDK together

Training only

pip install "praisonai-train[llm]" — LLM fine-tuning + agent training

Browser automation

pip install "praisonai-browser[all]" — Chrome extension + Playwright engine. Run playwright install chromium once before first browser use.

Sandbox backends only

pip install "praisonai-sandbox[docker]" — code-execution sandboxes and the compute providers behind tools_run_on= / run_in=, without the wrapper

Info

First browser use. pip install praisonai no longer downloads Playwright browsers. Install them on demand the first time you use a browser tool:

bash

playwright install chromium
# Docker / CI:
playwright install chromium --with-deps

This keeps the default install fast, small, and offline / air-gapped / CI-friendly. praisonai[browser] and praisonai[all] behave the same way — they include the Python packages but not the browser binaries. See Offline & CI Install.

What you get with pip install praisonai:

Full CLI, gateway, bots, and the praisonaiagents SDK.
Browser binaries: not included — run playwright install chromium on first use.

One-line installer (recommended for CLI users)

If you want the CLI end-to-end, the one-line installer provisions an isolated managed environment (uv tool → pipx) and wires your PATH — no changes to your global Python:

bash

curl -fsSL https://raw.githubusercontent.com/MervinPraison/PraisonAI/main/install.sh | sh

It is idempotent and safe to re-run. pip install praisonai is untouched — keep using it if you embed PraisonAI as a Python library.

Diagram

Environment-variable overrides:

Variable	Purpose
`PRAISONAI_VERSION=x.y.z`	Pin a specific version (default: latest)
`PRAISONAI_INSTALLER=uv\	pipx`	Force a specific tool manager
`PRAISONAI_NONINTERACTIVE=1`	Never prompt — suitable for CI

After installing, configure a provider key:

bash

praisonai setup

Installing PraisonAI

PraisonAI is published as six PyPI packages. Pick the one that matches what you want to do:

Diagram

Full (praisonai)

The complete package — CLI, gateway, bots, integrations, YAML-driven multi-bot orchestration. Pulls praisonai-code and praisonaiagents automatically.

Note

For gateway hot reload (event-driven gateway.yaml watching via watchdog), install the gateway extra: pip install "praisonai[gateway]".

[claw] extra: pip install "praisonai[claw]" installs the full wrapper plus praisonai-bot[gateway,bot] — the WebSocket gateway and Telegram/Discord/Slack channel bots. Use this when you want the full wrapper and all channel runtime features in one command. For gateway + bots without the wrapper, use pip install "praisonai-bot[gateway,bot]" directly (see Standalone Bot Gateway).

Sandbox extras: the sandbox backends live in the standalone praisonai-sandbox package. Install a cloud backend with pip install 'praisonai[docker]', 'praisonai[e2b]', 'praisonai[modal]', 'praisonai[daytona]' (needs DAYTONA_API_KEY), pip install 'praisonai-sandbox[ssh]', or pip install 'praisonai-sandbox[novita]' for the Novita backend (needs NOVITA_API_KEY). See Sandbox Backends for the full matrix. The praisonai[e2b], praisonai[docker], and praisonai[daytona] extras were fixed in PR #4073 — before that release they either did not exist or were empty. If pip warns does not provide the extra 'e2b', upgrade praisonai.

Create Virtual Environment (Optional)

Mac/Linux

python -m venv praisonai-env
source praisonai-env/bin/activate

Windows

python -m venv praisonai-env
.\praisonai-env\Scripts\activate

Install
Terminal
```
pip install praisonai
```
Configure Environment
Set your API key. PraisonAI auto-detects whichever provider credential is present:
OpenAI
```
export OPENAI_API_KEY="${OPENAI_API_KEY:?Set OPENAI_API_KEY in your shell}"
```
Anthropic
```
export ANTHROPIC_API_KEY="${ANTHROPIC_API_KEY:?Set ANTHROPIC_API_KEY in your shell}"
```
Gemini
```
export GEMINI_API_KEY="${GEMINI_API_KEY:?Set GEMINI_API_KEY in your shell}"
```
Groq
```
export GROQ_API_KEY="${GROQ_API_KEY:?Set GROQ_API_KEY in your shell}"
```
Ollama
```
# Only needed if Ollama is not on the default 127.0.0.1:11434
export OLLAMA_API_BASE=http://localhost:11434
```
Note
If you only set ANTHROPIC_API_KEY (or GEMINI_API_KEY, GOOGLE_API_KEY, GROQ_API_KEY, COHERE_API_KEY, or OLLAMA_HOST), praisonai run picks the matching provider’s default model automatically — no --model flag required. See Provider Auto-Detection for the full lookup table.

Tip
Running Ollama on the default 127.0.0.1:11434? Export nothing — praisonai run --model ollama/llama3.2 "hello" checks the server is reachable and runs with no key. With no --model, PraisonAI auto-detects a local endpoint when no cloud key is set. See Keyless local-first fallback.

Code (praisonai-code)

The standalone agent runtime — run, chat, code, and the full CLI backend, without the gateway/bot integrations. Depends only on praisonaiagents.

Create Virtual Environment (Optional)

Mac/Linux

python -m venv praisonai-env
source praisonai-env/bin/activate

Windows

python -m venv praisonai-env
.\praisonai-env\Scripts\activate

Install
Terminal
```
pip install praisonai-code
```
Configure Environment
bash
```
export OPENAI_API_KEY="${OPENAI_API_KEY:?Set OPENAI_API_KEY in your shell}"
```
Any supported provider key works. See Provider Auto-Detection.

Run an agent

python

from praisonaiagents import Agent

agent = Agent(name="assistant", instructions="Be helpful")
response = agent.start("Summarise the top AI news today")
print(response)

Bot (praisonai-bot)

Standalone bots and gateway — no full wrapper. Depends on praisonaiagents only at PyPI level.

Install

Terminal

pip install "praisonai-bot[gateway,bot]"

Configure Environment

bash

export OPENAI_API_KEY="${OPENAI_API_KEY:?Set OPENAI_API_KEY in your shell}"
export TELEGRAM_BOT_TOKEN="${TELEGRAM_BOT_TOKEN:?Set TELEGRAM_BOT_TOKEN in your shell}"

Start gateway

Terminal

praisonai-bot gateway start --host 127.0.0.1 --port 8765

See the praisonai-bot SDK page for Python API details.

Train (praisonai-train)

Standalone training tier — LLM fine-tuning via Unsloth and iterative agent training, without the full wrapper. Depends on praisonaiagents only at PyPI level.

Create Virtual Environment (Optional)

Mac/Linux

python -m venv praisonai-env
source praisonai-env/bin/activate

Windows

python -m venv praisonai-env
.\praisonai-env\Scripts\activate

Install
Terminal
```
pip install "praisonai-train[llm]"
```
Note
LLM fine-tuning needs Python 3.11, CUDA 12.4, and torch>=2.6 (plus unsloth>=2025.9.1, trl>=0.18.2, transformers>=4.51.3). Agent training (pip install praisonai-train) has no such requirement.
Configure Environment
bash
```
export OPENAI_API_KEY="${OPENAI_API_KEY:?Set OPENAI_API_KEY in your shell}"
```
Any supported provider key works. See Provider Auto-Detection.
Run the trainer
Terminal
```
praisonai-train --help
```

See the praisonai-train Package page for fine-tuning and agent-training details.

Browser (praisonai-browser)

Standalone browser tier — the bridge server, CDP agent, and Playwright engine for Chrome automation, without the full wrapper. Depends on praisonaiagents only at PyPI level.

Create Virtual Environment (Optional)

Mac/Linux

python -m venv praisonai-env
source praisonai-env/bin/activate

Windows

python -m venv praisonai-env
.\praisonai-env\Scripts\activate

Install
Terminal
```
pip install "praisonai-browser[all]"
```
Install a browser engine (once)
Terminal
```
playwright install chromium
# Docker / CI (adds OS-level deps):
playwright install chromium --with-deps
```
Note
No browser binaries are downloaded automatically by pip install in any tier — they are provisioned on demand. See Offline & CI Install.
Configure Environment
bash
```
export OPENAI_API_KEY="${OPENAI_API_KEY:?Set OPENAI_API_KEY in your shell}"
```
Any supported provider key works. See Provider Auto-Detection.

Run a goal

Terminal

praisonai-browser run "Go to google and search praisonai"

See the praisonai-browser Package page and the Browser CLI for the full command set.

Agents (SDK only)

The pure Python SDK — no CLI, no gateway, no heavy dependencies. Import directly in your own application.

Create Virtual Environment (Optional)

Mac/Linux

python -m venv praisonai-env
source praisonai-env/bin/activate

Windows

python -m venv praisonai-env
.\praisonai-env\Scripts\activate

Install
Terminal
```
pip install praisonaiagents
```

Configure Environment

bash

export OPENAI_API_KEY="${OPENAI_API_KEY:?Set OPENAI_API_KEY in your shell}"

Use in your app

python

from praisonaiagents import Agent

agent = Agent(name="assistant", instructions="Be helpful")
response = agent.start("Hello!")
print(response)

No Code

Create Virtual Environment (Optional)

Mac/Linux

python -m venv praisonai-env
source praisonai-env/bin/activate

Windows

python -m venv praisonai-env
.\praisonai-env\Scripts\activate

Install PraisonAI
bash
```
pip install praisonai
```
Set API Key
Set your API key for the provider you want to use. PraisonAI auto-detects whichever credential is present:
bash
```
export OPENAI_API_KEY="${OPENAI_API_KEY:?Set OPENAI_API_KEY in your shell}"
```
Use Anthropic, Gemini, Groq, or Ollama instead? Just set that provider’s key and praisonai run picks the right model automatically. See Provider Auto-Detection.

JavaScript

Install PraisonAI
bash
```
npm install praisonai
```

Set API Key

bash

export OPENAI_API_KEY="${OPENAI_API_KEY:?Set OPENAI_API_KEY in your shell}"

TypeScript

Install PraisonAI
bash
```
npm install praisonai
```

Set API Key

bash

export OPENAI_API_KEY="${OPENAI_API_KEY:?Set OPENAI_API_KEY in your shell}"

Package dependency chain

Diagram

Each layer depends on the one to its left. Installing praisonai also pulls praisonai-sandbox (the code-execution backends) alongside praisonai-code; installing praisonai-code pulls only praisonaiagents; installing praisonaiagents has no PraisonAI dependencies.

Generate your OpenAI API key from OpenAI You can also use other LLM providers like Anthropic, Google, etc. Please refer to the Models for more information.

Which Install Do You Need?

Terminal-only (smaller)

pip install praisonai-code — agentic CLI: run, chat, code, runtime. No bots or gateway.

Full (default)

pip install praisonai — everything: bots, gateway, kanban, dashboard, and the agentic CLI.

How It Works

Pip installs the package, you export one provider key, and the CLI or SDK resolves the matching model at run time.

Diagram

Best Practices

Install only what you need

Use praisonaiagents for a pure Python SDK, praisonai-code for the terminal runtime, and praisonai for the full wrapper with bots and gateway.

Use a virtual environment

Create a venv before installing to keep PraisonAI isolated from your system Python.

Export keys, don't hard-code them

Set OPENAI_API_KEY (or your provider’s key) in your shell or .env. Never inline the raw value in code.

Skip –model on first runs

PraisonAI auto-detects the provider from whichever key is present and picks a sensible default model.

Quick Start

Build your first AI agent.

Models

Choose a provider and model.

Quick Install

macOS / Linux / WSL

bash

curl -fsSL https://raw.githubusercontent.com/MervinPraison/PraisonAI/main/install.sh | sh

Windows

powershell

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

Installs praisonai[all] into %USERPROFILE%\.praisonai\venv, wires PATH, and runs praisonai setup on first install. See Installer Internals for parameters and env-var overrides.

To install with specific extras only:

powershell

& ([scriptblock]::Create((iwr -useb https://praison.ai/install.ps1))) -Extras "ui,chat"

Alternative (no installer): pipx install praisonai or pip install "praisonai[all]".

Note

Windows terminals: PraisonAI automatically detects legacy Windows code pages (CP1252, CP850, etc.) and falls back to ASCII-safe output. For full emoji and box-drawing rendering, switch your terminal to UTF-8:

PowerShell

$env:PYTHONIOENCODING='utf-8'
chcp 65001

CMD

set PYTHONIOENCODING=utf-8
chcp 65001

Manage Your Install

Upgrade

praisonai upgrade — update the CLI in place, or --check for a newer version

Uninstall

praisonai uninstall — remove the managed install cleanly

Package Structure

PraisonAI ships as three separate PyPI packages. Understanding which to install avoids surprises at runtime.

Diagram

Install command	What you get	Agentic CLI (`run`, `chat`, `code`, …)	Bot / gateway / pairing
`pip install praisonai`	Wrapper + code + agents	✅ Full	✅ Yes
`pip install praisonai-code`	Terminal-native agent CLI + LLM runtime	✅ Default `run "…"`, `run –output plain	verbose	silent	actions	json	stream	stream-json`,` chat`,` code `(resident TUI, PR #3818),` daemon`,` doctor`,` config`,` version`	❌ No — needs `pip install praisonai`
`pip install praisonaiagents`	Core SDK — Python API only	❌ No CLI	N/A

PyPI publish order

Packages are published in dependency order:

1. praisonaiagents  →  2. praisonai-code + praisonai-bot + praisonai-train + praisonai-browser  →  3. praisonai

If you pin versions, ensure all six packages resolve to the same release cycle.

Since 4.6.104, praisonai pins praisonai-code>=0.0.2, so pip install praisonai always pulls a compatible runtime automatically. See praisonaiagents SDK page for the release-cycle notes.

Installation

One-line installer (recommended for CLI users)

Installing PraisonAI

Full (praisonai)

Code (praisonai-code)

Bot (praisonai-bot)

Train (praisonai-train)

Browser (praisonai-browser)

Agents (SDK only)

No Code

JavaScript

TypeScript

Package dependency chain

Which Install Do You Need?

How It Works

Best Practices

Related

Quick Install

macOS / Linux / WSL

Windows

Manage Your Install

Package Structure

PyPI publish order