Skip to content

Quick Start Guide

Get started with wags by connecting to existing wags servers.

Prerequisites

Installation

⚠️ Warning: wags is based on ongoing research and is under active development. Features and APIs may change.

Bash
# Clone the repository
git clone https://github.com/chughtapan/wags.git
cd wags

# Create and activate virtual environment
uv venv
source .venv/bin/activate

# Install the package in development mode
uv pip install -e ".[dev]"

Verify Installation

Bash
wags version

You should see:

Text Only
WAGS version 0.1.0
FastMCP version x.x.x

Getting Started

The easiest way to connect to wags servers is using the wags run command:

Bash
# Connect to all configured servers
wags run

# Connect to specific servers only
wags run --servers github

# Use a different model (any fast-agent model name, e.g. gpt-6.1-sol or claude-opus-5-5)
wags run --model opus

wags run invokes fast-agent with a configuration file (servers/fastagent.config.yaml) and basic instructions (src/wags/utils/agent_instructions.txt), and connects to all servers by default. You can configure which servers to connect to using the --servers flag or create your own configuration and instruction files - see the fast-agent documentation for more details.

Next Steps