Documentation

iauto

iauto is a low-code engine for building and deploying AI agents.

• AI: Cutting-edge AI capabilities.
• Low-Code: Define your agents using YAML.
• Automation: Integrated automation frameworks like Appium and Playwright.
• Extensible: Well-designed Python API.

News

• Integrated autogen: Create your Multi-Agent system efficiently with iauto.
• Run most open source LLMs locally using llama.cpp and llama-cpp-python.

Quick Start

Installation

Python version requirement: >=3.8

iauto can be installed from PyPI using pip. It is recommended to create a new virtual environment before installation to avoid conflicts.

pip install -U iauto

If you want to run LLM locally, you can enable hardware acceleration in the following ways.

To enable cuBLAS acceleration on NVIDIA GPU:

CMAKE_ARGS="-DGGML_CUBLAS=ON" pip install -U iauto

To enable Metal on Apple silicon devices:

CMAKE_ARGS="-DGGML_METAL=ON" pip install -U iauto

Command-line tool

Usage:

python -m iauto --help

or

ia --help

Run playbook:

ia run ./your-plabook.yaml

Example playbooks

Playground

iauto provides a web-based application for running playbooks, LLM Chat, ReAct reasoning, and Multi-Agent tasks.

Launch playground:

ia playground

Screenshot:

Contribution

We are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.

Development setup

• Code Style: PEP-8
• Docstring Style: Google Style

# Create python venv
python -m venv .venv
source .venv/bin/activate

# Install dependencies
pip install -r requirements.txt
pip install -r requirements-dev.txt

# Apply autopep8, isort and flake8 as pre commit hooks
pre-commit install

Build

./build.sh

License

MIT

icon license: https://openmoji.org/library/emoji-1F9BE