Installation - Augent

One-line install

curl -fsSL https://augent.app/install.sh | bash

Works on macOS and Linux. Handles all dependencies, installs Augent, and configures MCP. The rest of this page breaks down exactly what runs, provides a manual alternative, and documents how to fully remove Augent.

What the installer does

The installer is a single bash script. The source is public and auditable: install.sh. It runs three phases:

Phase 1: System dependencies

Detects your OS and package manager, then installs anything not already present. Every dependency is open source and widely adopted:

Package	What it is	macOS	Linux
Python 3.12	Language runtime	`brew install python@3.12`	`apt install python3` or equivalent
FFmpeg	Industry-standard audio/video toolkit	`brew install ffmpeg`	`apt install ffmpeg` or equivalent
yt-dlp	Media downloader	`brew install yt-dlp`	`pip install yt-dlp`
aria2	Multi-connection download accelerator	`brew install aria2`	`apt install aria2` (macOS and Debian only)
espeak-ng	Speech synthesis phonemizer	`brew install espeak-ng`	`apt install espeak-ng` (macOS and Debian only)
Homebrew	macOS package manager	Installed if missing	N/A

Already-installed packages are skipped. Version requirements: Python 3.10–3.13, no minimum for the rest.On Fedora, the installer also enables RPMFusion to provide FFmpeg.

Phase 2: Augent + Python packages

Installs Augent and all Python packages via pip from the GitHub repo. Every package is open source and installed from PyPI:

Package	What it is	Source
faster-whisper	OpenAI Whisper reimplementation, optimized for speed	SYSTRAN
PyTorch	ML framework used by the models below	Meta / PyTorch Foundation
sentence-transformers	Text embeddings for semantic search	UKP Lab
pyannote-audio	Speaker diarization	CNRS research lab
Kokoro	Text-to-speech (54 voices, 9 languages)	hexgrad
Demucs	Audio source separation	Meta Research
FastAPI	Web framework for the local UI (optional `web` extra)	Tiangolo

Also downloads the audio-downloader shell script to ~/.local/bin/.If the full install fails (common on some platforms due to ML package constraints), it falls back to installing the core package first, then each optional extra individually, reporting what succeeded and what was skipped.

Phase 3: Configuration

PATH: if ~/.local/bin or your Python user bin directory isn’t in your PATH, an export line is appended to ~/.zshrc or ~/.bashrc
Package verification: imports each installed module to confirm nothing broke during install
Speaker models: downloads pre-packaged pyannote speaker diarization models (~29MB) from GitHub Releases to ~/.cache/huggingface/hub/. Skipped if already cached
MCP registration: runs claude mcp add augent -s user to register the MCP server with Claude Code. If Claude Code isn’t installed, it prints the command for you to run later. If OpenClaw is detected, it also configures MCP and installs the Augent skill there

When piped from curl, MCP configuration runs automatically. When run interactively (e.g., bash install.sh from a local clone), it prompts first.

After installing, you can optionally create ~/.augent/config.yaml to customize default model size, output directories, and more. See Configuration.

What the installer does not do


No root/sudo on macOS	Homebrew manages its own directory permissions. The installer never calls sudo on macOS.
No background processes	No daemons, launch agents, systemd services, or cron jobs are created.
No telemetry	No analytics, no tracking, no phone-home. All network activity is package installation from GitHub, PyPI, and Homebrew. On Fedora, RPMFusion is also contacted for FFmpeg.
No system file modifications	Outside of standard package manager operations on Linux, the installer only writes to your home directory (`~/.local/bin`, shell rc file, `~/.cache/huggingface/`, Claude Code config).

On Linux, sudo is used strictly for system package manager commands (apt install, dnf install, etc.): the same commands you would run by hand.

Manual install

Pick your platform. Each tab is a complete flow from start to finish.

macOS
Ubuntu / Debian
Fedora
Arch
Windows

1. System dependencies

brew install python@3.12 ffmpeg yt-dlp aria2 espeak-ng

2. Augent

pip install "augent[all] @ git+https://github.com/AugentDevs/Augent.git@main" --break-system-packages

--break-system-packages is required on Homebrew Python due to PEP 668. This is safe: Homebrew Python is not your system Python.

3. audio-downloader

mkdir -p ~/.local/bin
curl -fsSL https://raw.githubusercontent.com/AugentDevs/Augent/main/bin/audio-downloader -o ~/.local/bin/audio-downloader
chmod +x ~/.local/bin/audio-downloader

Add to PATH if not already present:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc
source ~/.zshrc

4. MCP server

claude mcp add augent -s user -- python3 -m augent.mcp

5. Verify

augent --help
audio-downloader --help

Restart Claude Code and run /mcp to confirm.

1. System dependencies

sudo apt update
sudo apt install python3 python3-pip python3-venv ffmpeg espeak-ng aria2
pip install yt-dlp

2. Augent

pip install "augent[all] @ git+https://github.com/AugentDevs/Augent.git@main" --user

3. audio-downloader

mkdir -p ~/.local/bin
curl -fsSL https://raw.githubusercontent.com/AugentDevs/Augent/main/bin/audio-downloader -o ~/.local/bin/audio-downloader
chmod +x ~/.local/bin/audio-downloader

Add to PATH if not already present:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc

4. MCP server

claude mcp add augent -s user -- python3 -m augent.mcp

5. Verify

augent --help
audio-downloader --help

Restart Claude Code and run /mcp to confirm.

1. System dependenciesFFmpeg requires RPMFusion:

sudo dnf install https://download1.rpmfusion.org/free/fedora/rpmfusion-free-release-$(rpm -E %fedora).noarch.rpm
sudo dnf install python3 python3-pip ffmpeg espeak-ng aria2
pip install yt-dlp

2. Augent

pip install "augent[all] @ git+https://github.com/AugentDevs/Augent.git@main" --user

3. audio-downloader

mkdir -p ~/.local/bin
curl -fsSL https://raw.githubusercontent.com/AugentDevs/Augent/main/bin/audio-downloader -o ~/.local/bin/audio-downloader
chmod +x ~/.local/bin/audio-downloader

Add to PATH if not already present:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc

4. MCP server

claude mcp add augent -s user -- python3 -m augent.mcp

5. Verify

augent --help
audio-downloader --help

Restart Claude Code and run /mcp to confirm.

1. System dependencies

sudo pacman -S python python-pip ffmpeg espeak-ng aria2 yt-dlp

2. Augent

pip install "augent[all] @ git+https://github.com/AugentDevs/Augent.git@main" --user

3. audio-downloader

mkdir -p ~/.local/bin
curl -fsSL https://raw.githubusercontent.com/AugentDevs/Augent/main/bin/audio-downloader -o ~/.local/bin/audio-downloader
chmod +x ~/.local/bin/audio-downloader

Add to PATH if not already present:

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc

4. MCP server

claude mcp add augent -s user -- python3 -m augent.mcp

5. Verify

augent --help
audio-downloader --help

Restart Claude Code and run /mcp to confirm.

1. System dependenciesInstall Python 3.12 and FFmpeg. Make sure both are added to your PATH during installation.Install yt-dlp:

pip install yt-dlp

2. Augent

pip install "augent[all] @ git+https://github.com/AugentDevs/Augent.git@main"

3. MCP server

claude mcp add augent -s user -- python -m augent.mcp

4. Verify

augent --help

Restart Claude Code and run /mcp to confirm.

audio-downloader is a bash script and is not available on native Windows. Audio downloading is still available through the download_audio MCP tool and the augent CLI, which use yt-dlp directly.

Uninstall

macOS / Linux
Windows

Remove Augent:

pip uninstall augent -y
rm -f ~/.local/bin/audio-downloader
claude mcp remove augent -s user
rm -rf ~/.augent

Remove speaker models installed by the installer:

rm -rf ~/.cache/huggingface/hub/models--pyannote--speaker-diarization-3.1
rm -rf ~/.cache/huggingface/hub/models--pyannote--segmentation-3.0

If you used OpenClaw:

rm -rf ~/.openclaw/skills/augent

Also remove the augent entry from ~/.openclaw/openclaw.json if present.

Other ML models (Whisper, sentence-transformers, Kokoro) are downloaded on first use and cached under ~/.cache/huggingface/hub/. These are shared with other HuggingFace tools. Only remove them if nothing else on your system uses them.

pip uninstall augent -y
claude mcp remove augent -s user

Augent stores local data under %USERPROFILE%\.augent\. To remove it completely, delete that folder.Speaker diarization models are cached at %USERPROFILE%\.cache\huggingface\hub\. To remove them, delete the models--pyannote--speaker-diarization-3.1 and models--pyannote--segmentation-3.0 folders.

​One-line install

​What the installer does

​What the installer does not do

​Manual install

​Uninstall

One-line install

What the installer does

What the installer does not do

Manual install

Uninstall