-
Notifications
You must be signed in to change notification settings - Fork 1
Installation
Varun Pratap Bhardwaj edited this page Mar 6, 2026
·
1 revision
- Python 3.10 or later
- pip (Python package manager)
The simplest way to install AgentAssay:
pip install agentassayThis installs the core package with all required dependencies.
To use AgentAssay with a specific agent framework, install the corresponding extra:
# For LangGraph agents
pip install agentassay[langgraph]
# For CrewAI agents
pip install agentassay[crewai]
# For AutoGen agents
pip install agentassay[autogen]
# For OpenAI Agents SDK
pip install agentassay[openai]
# For smolagents
pip install agentassay[smolagents]
# Install all framework adapters
pip install agentassay[all]If you use AgentAssert for behavioral contracts, install the contracts extra:
pip install agentassay[contracts]For the interactive Streamlit dashboard:
pip install agentassay[dashboard]For development or to get the latest unreleased changes:
# Clone the repository
git clone https://github.com/qualixar/agentassay.git
cd agentassay
# Create a virtual environment (recommended)
python -m venv .venv
source .venv/bin/activate # macOS/Linux
# .venv\Scripts\activate # Windows
# Install in editable mode with dev dependencies
pip install -e ".[dev]"The [dev] extra includes everything needed for contributing:
- Test runner and coverage tools
- Linter and formatter
- Type checker
- Property-based testing support
After installing, verify that everything is working:
# Check the CLI is available
agentassay --version
# Check the pytest plugin is registered
python -m pytest --co -q 2>&1 | head -5
# Run a quick Python import check
python -c "import agentassay; print(f'AgentAssay v{agentassay.__version__}')"Expected output:
agentassay, version 0.1.0
AgentAssay v0.1.0
pip install --upgrade agentassaypip uninstall agentassay- Quick Start — Test your first agent in 5 minutes
- Supported Frameworks — See all framework adapters
- CLI Reference — Explore CLI commands
Part of Qualixar | Author: Varun Pratap Bhardwaj
Getting Started
Core Concepts
- Token-Efficient Testing
- Behavioral Fingerprinting
- Statistical Methods
- Coverage Model
- Mutation Testing
Guides
Reference