Skip to main content

​
Getting Started

1

Fork the repo

Fork AugentDevs/Augent on GitHub.
2

Clone your fork

git clone https://github.com/YOUR_USERNAME/Augent.git
cd Augent
3

Create a branch

git checkout -b my-feature
Use a descriptive branch name: fix-memory-bug, add-wav-support, docs-typo, etc.
4

Install in development mode

pip install -e ".[dev,all]"
This installs Augent with all optional dependencies (speakers, semantic search, TTS, web UI) plus dev tools (pytest, black, ruff) in editable mode.
5

Verify everything works

pytest tests/ -v

​
Requirements

  • Python 3.10+
  • ffmpeg (for audio processing)
  • aria2 (for fast downloads)
  • yt-dlp (for audio downloading)

​
Run tests

pytest tests/ -v --tb=short
Tests run on Python 3.10, 3.11, 3.12, and 3.13 via CI.

​
Lint & format

# Check
ruff check .
black --check .

# Auto-fix
ruff check . --fix
black .

​
Run the MCP server locally

augent-mcp

​
Config overrides

User config lives at ~/.augent/config.yaml and is loaded by augent/config.py. During development, create this file to test config overrides (model size, output directories, disabled tools). See Configuration.