The Operating System for Autonomous Software Teams
Project description
Squadron
The Operating System for Autonomous Software Teams
Give your AI agents a job. Not just a prompt.
Problem • Solution • Quick Start • Usage • Architecture • Roadmap
🎬 See It In Action
$ squadron report --msg "Refactored the auth module." --ticket "KAN-1"
🚀 Squadron Bridge Activated...
✅ Slack: Message sent to #dev-updates
✅ Jira: Comment added to KAN-1
One command. Two integrations. Zero context switching.
😤 The Problem
You're building with AI agents. They're powerful. They can write code, refactor systems, and solve complex problems.
But here's the frustrating reality:
| What You Want | What Actually Happens |
|---|---|
| Agent finishes a task | You don't know unless you check the terminal |
| Jira ticket should update | It stays in "To Do" forever |
| Team needs visibility | They have no idea what the AI is building |
Your agents are trapped in a chat window. They can think, but they can't act in your team's workflow.
✨ The Solution
Squadron is a bridge that connects your local AI agents to your team's real tools.
┌─────────────────┐ ┌─────────────────┐
│ AI AGENT │ │ YOUR TEAM │
│ (Cursor, etc) │ │ │
│ │ │ 📋 Jira │
│ "Task done!" │────────▶│ 💬 Slack │
│ │Squadron │ 🔔 Discord │
│ │ Bridge │ 🐙 GitHub │
└─────────────────┘ └─────────────────┘
Squadron gives your agents:
- 🗣️ A Voice — Post updates to Slack/Discord
- ✋ Hands — Update Jira tickets, change statuses
- 🧠 Context — Knowledge files that define your workflow
🚀 Quick Start
1. Install
git clone https://github.com/MikeeBuilds/squadron.git
cd squadron
pip install -e .
2. Configure
Create a .env file in your project root:
# Jira
JIRA_SERVER=https://your-domain.atlassian.net
JIRA_EMAIL=your-email@example.com
JIRA_TOKEN=your-api-token
# Slack
SLACK_BOT_TOKEN=xoxb-your-bot-token
3. Test
squadron report --msg "Hello from Squadron!" --channel "#general"
If you see ✅ Slack: Message sent — you're live! 🎉
📖 Usage
Basic Report (Slack Only)
squadron report --msg "Starting the database migration"
Report + Jira Update
squadron report --msg "Fixed the login bug" --ticket "PROJ-101"
Report + Jira Status Transition
squadron report --msg "Feature complete" --ticket "PROJ-101" --status "Done"
Full Command
squadron report \
--msg "Refactored RBI pipeline logic" \
--ticket "KAN-42" \
--channel "#dev-updates" \
--status "In Review"
🏗️ Architecture
Squadron uses a Skill-Based Architecture inspired by the Model Context Protocol (MCP).
squadron/
├── cli.py # 🎯 The Router (entry point)
│
├── skills/ # 🛠️ ACTION LAYER (The Hands)
│ ├── jira_bridge/
│ │ ├── tool.py # Jira API integration
│ │ └── SKILL.md # Instructions for agents
│ └── slack_bridge/
│ ├── tool.py # Slack API integration
│ └── SKILL.md # Instructions for agents
│
└── knowledge/ # 🧠 CONTEXT LAYER (The Brain)
├── TEAM.md # Who is on the team?
├── WORKFLOW.md # How does work flow?
└── ROLES.md # What does each agent do?
Why This Structure?
| Layer | Purpose | Example |
|---|---|---|
| Skills | Executable actions | JiraTool.update_ticket() |
| Knowledge | Context for decisions | "Move to Done only after tests pass" |
Skills = Hands. Knowledge = Brain.
🤖 Teaching Your Agents
Add this to your agent's system prompt or SKILL.md:
## Tool: Squadron
You have access to the `squadron` CLI for team communication.
### When to use:
- After completing a coding task
- When you hit a blocker and need help
- To update ticket status
### Commands:
- Start task: `squadron report --msg "Starting work on auth" --ticket "KAN-1" --status "In Progress"`
- Complete task: `squadron report --msg "Auth module complete" --ticket "KAN-1" --status "Done"`
- Report blocker: `squadron report --msg "Blocked: Need API keys" --ticket "KAN-1"`
🗺️ Roadmap
- Core CLI —
squadron reportcommand - Jira Integration — Comments + status transitions
- Slack Integration — Rich block messages
- Discord Integration — Webhook support
- GitHub Skill — Open PRs, merge branches
- Overseer Mode — Wake agents when tickets are assigned
- PyPI Release —
pip install squadron-agents
🌟 The Origin Story
Squadron was born out of necessity.
We're building BlackCircleTerminal, a quantitative trading platform managed by AI agents. Our virtual developers — Marcus (Strategy) and Caleb (Data) — needed a way to communicate with us when we weren't at the keyboard.
We realized that for agents to be truly useful, they need to be part of the workflow, not just the code editor.
Squadron is the nervous system that connects our AI workforce to our human tools.
🤝 Contributing
We're building the future of Agent-First Development. Want to add a new skill?
- Fork the repo
- Create a skill in
squadron/skills/your_skill/ - Add
tool.py(logic) andSKILL.md(instructions) - Open a PR!
Ideas for new skills:
- Linear / Trello / Asana integrations
- Email notifications
- CI/CD triggers
- Calendar scheduling
📜 License
MIT © MikeeBuilds
Don't just build agents. Give them a job.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file squadron_agents-0.1.0.tar.gz.
File metadata
- Download URL: squadron_agents-0.1.0.tar.gz
- Upload date:
- Size: 13.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c44e75134409cd258c08e896b61d13e6be55575ba7d3bc260e31c2eb025773b0
|
|
| MD5 |
8cb2c16b2e01a15feb22902e083372fb
|
|
| BLAKE2b-256 |
bc909c2cd92c3c84977fa5ca50a60717f9ac2112679b32af1c03a9ccc33567f7
|
File details
Details for the file squadron_agents-0.1.0-py3-none-any.whl.
File metadata
- Download URL: squadron_agents-0.1.0-py3-none-any.whl
- Upload date:
- Size: 13.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cb5decb757a8dec24cf4422d34671c4e839ca251f25a2cc0d6341db585f96d8d
|
|
| MD5 |
b01f633cee3de88c15119b970e8a6003
|
|
| BLAKE2b-256 |
fb823f0567311bd3d6dd233ba367fd5ae2d76d7b276f96c2e4266d45436664e8
|