Create AI agent projects from the command line.

• Quickstart Guide – How to create a new agent project.
• Video Tutorial – Follow along and build a web scrape agent with AgentStack

AgentStack works on macOS, Windows, and Linux.
If something doesn't work, please file an issue.
If you have questions or need help, please ask in our Discord community.

🛠️🏃🏼‍♀️ The quickest way to build your powerful agent project

AgentStack serves as a great tool for starting your agent project and offers many CLI utilities for easy code-gen throughout the development process.

AgentStack is not a low-code alternative to development. Developers will still need an understanding of how to build with their selected agent framework.

# Install UV package manager
pip install uv

# Create a development environment
uv venv
source .venv/bin/activate

# Install AgentStack in development mode
uv pip install -e "/Users/bastiannisnaciovenegasarevalo/uvAsTackCloneT-2/actualCustomRepo/uvAgentStack[dev]"

# Create your project
uv run agentstack init <project_name>

You don't need to install or configure tools like LangChain or LlamaIndex.
They are preconfigured and hidden so that you can focus on the code.

Create a project, and you're good to go.

You'll need to have Python 3.10+ on your local development machine. We recommend using the latest version. You can use pyenv to switch Python versions between different projects.

To create a new agent project:

1. First, install and set up UV:

pip install uv
uv venv
source .venv/bin/activate

2. Install AgentStack in development mode:

uv pip install -e "/Users/bastiannisnaciovenegasarevalo/uvAsTackCloneT-2/actualCustomRepo/uvAgentStack[dev]"

3. Create your project:

uv run agentstack init <project_name>

It will create a directory with your project name inside the current folder.
Inside that directory, it will generate the initial project structure and create a new virtual environment.

No configuration or complicated folder structures, only the files you need to build your agent project.
Once the initialization is done, you can follow the setup instructions to get your project running:

1. Navigate to your project:

cd <project_name>

2. Create and activate project environment:

uv venv
source .venv/bin/activate

3. Lock and Install project dependencies:

uv lock
uv sync

Additionally, pre-built templates are available as a shortcut to building your project. View the available templates.

After generating a project, the next step is to build your agent project by creating Agents and Tasks. You can do this quickly with AgentStack:

uv run agentstack generate agent/task <name>

Modify the agents and tasks by changing the agents.yaml and tasks.yaml configuration files in src/config

One of AgentStack's core principles is to establish the de facto agent stack. A critical component of this stack is the tooling and functionality given to agents beyond simply LLM capabilities.

AgentStack has worked to make access to tools as easy as possible, staying framework agnostic and featuring the best tools.

A list of all tools can be found on our docs.

Adding tools is as simple as

uv run agentstack tools add

uv run agentstack run

Runs the agent project in development mode.

Note: Always use uv run when executing AgentStack commands to ensure proper environment management.

👀 Support for easy production deployment of agents is coming soon.

To make working with AgentStack more convenient, you can set up an alias for the uv run agentstack command:

Add this to your ~/.bashrc, ~/.zshrc, or equivalent:

alias agentstack='uv run agentstack'

Add this to your PowerShell profile:

Set-Alias -Name agentstack -Value "uv run agentstack"

After setting up the alias, you can use agentstack commands directly:

agentstack init <project_name>
agentstack run
agentstack generate agent <name>

Note: The alias needs to be set up in each new shell session unless added to your shell's configuration file.

• Agents should be easy: There are so many frameworks out there, but starting from scratch is a pain. Similar to create-react-app, AgentStack aims to simplify the "from scratch" process by giving you a simple boilerplate of an agent. It uses popular agent frameworks and LLM providers, but provides a cohesive curated experience on top of them.

• No Configuration Required: You don't need to configure anything. A reasonably good configuration of both development and production builds is handled for you so you can focus on writing code.

• No Lock-In: You can customize your setup at any time. AgentStack is designed to make it easy to get the components you need running right off the bat; it's up to you what to do next.

AgentStack is not designed to be a low-code solution to building agents. Instead it is a great head-start for starting an agent project from scratch.

Development of AgentStack is being done primarily on CrewAI. We will soon be working to make AgentStack fully framework-agnostic, meaning that any supported multi-agent framework can be used for your project.

• Core Tools built by AgentStack
• Preferred partners in the package directly
• Community partner tools added through external repositories

• Generated testing
• Integrated benchmarking
• Easy integration of tools for browsing, RAG, and more.
• A fast interactive test runner with built-in support for coverage reporting.
• A live development server that warns about common mistakes.
• A build script to bundle your project for production.

AgentStack is open source software licensed as MIT.

AgentStack is a new project built by passionate AI agent developers! We'd love help making this tool better. Easy first issues are available, create new issues with feature ideas, or chat with us on our Discord.

If you are an Agent Tool developer, feel free to create an issue or even a PR to add your tool to AgentStack.