Our take
Inactiveno commits in over a year- Activity
- 19
- Community
- 63
- Issues
- 21
- Pull requests
- 20
-1 stars in the last 30 days
AgentStack is a practical Python starter CLI for agent developers, but its inactive maintenance status makes it worth evaluating carefully before adopting it for a new project.
Good fit if
- You want a scaffold and code-generation utilities, and are comfortable building with the underlying agent framework yourself.
- Your project uses a supported framework such as CrewAI, LangGraph, OpenAI Swarms, or LlamaStack.
- You need an MIT-licensed starting point that runs on macOS, Windows, or Linux.
Look elsewhere if
- You need a project with recent maintenance: there have been no commits in over a year, and no releases in the past year.
- You need deployment support or a low-code agent builder, neither of which the README presents as a current offering.
- Your chosen framework is not among the supported options.
All health signals
| Last commit | 2025-07-11 (1.3 years ago) |
|---|---|
| Commits, last 90 days | 0 |
| Releases, last 12 months | 0 (latest 0.3.7, 2025-07-10) |
| Contributors | 26 (top contributor: 45% of commits) |
| Issues closed, last 90 days | 0 |
| Pull requests merged, last 90 days | 0 |
| Project age | 2 years |
Checked on 2026-10-29 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
2,198Forks
223Change since Nov 14, 2026: 0 stars·0 forks
Overview
AgentStack is a Python command-line tool for scaffolding an agent stack: the technologies and utilities that make up an AI agent project. It gives developers a starting structure and CLI utilities for generating code, so they can focus on building agent behavior instead of setting up a project from scratch. It runs on macOS, Windows, and Linux.
The project supports frameworks including CrewAI, LangGraph, OpenAI Swarms, and LlamaStack, with LLM providers accessed through LiteLLM or LangChain. AgentStack describes itself as a customizable starting point, not a low-code alternative to understanding and developing with your chosen framework.
Key Features
- Initialize an agent project with
agentstack initand install its transitive dependencies. - Generate agents and tasks from the command line.
- Configure agents and tasks using
agents.yamlandtasks.yamlfiles. - Add framework-agnostic tools with
agentstack tools add. - Run a generated project in development mode with
agentstack run. - Start from prebuilt project templates.
- Use supported agent frameworks including CrewAI, LangGraph, OpenAI Swarms, and LlamaStack.
- Get AgentOps observability support built in by default.
Use Cases
- An AI developer starting a new agent project who wants a ready-to-edit scaffold rather than assembling the initial structure by hand.
- A team evaluating supported agent frameworks that wants a consistent project starting point and access to common tools.
- A developer prototyping an agent with generated agents and tasks, then editing its configuration and code directly.
- A project using AgentOps that wants its observability support included in the initial setup.
What you need
Detected in the repository
- Python >=3.10 (from pyproject.toml)
- A test suite and automated checks on GitHub Actions
License in plain words
MITpermissive
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the copyright and license notice
- Share your changes: no
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
The project requires Python 3.10 or newer. Install AgentStack and initialize a project:
uv pip install agentstack
agentstack init <project_name>
See the README and Quickstart Guide for setup and usage details.
Alternatives
- agent-factory: Agent Factory creates executable Python agent workflows from natural-language tasks, while AgentStack scaffolds a starting project with agent frameworks and tools.
- adl-cli: adl-cli generates A2A server projects from YAML definitions for several languages, while AgentStack scaffolds Python agent projects with development tools.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| AgentStack | Python | MIT | 2.2k | Inactive |
| agent-factory | Python | Apache-2.0 | 115 | Inactive |
| adl-cli | Go | Apache-2.0 | 15 | Active |
Considerations
The health data marks the project inactive: it has had no commits in over a year, and there has been no recent release, issue-closing activity, or merged pull request activity. The repository has contributors beyond a single dominant contributor, but that does not offset the lack of recent maintenance signals. Teams should assess whether the supported frameworks and generated project structure still match their needs before relying on it.
The README says production deployment support is forthcoming and lists several capabilities, including generated testing and benchmarking, as roadmap items rather than current features. AgentStack is MIT-licensed, and its Python 3.10+ requirement applies to local development.
Found this useful?
Share it with someone who would like AgentStack.