BusyBee
Provides automatic commit functionality after each feature implementation, managing version control within the autonomous development workflow
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@BusyBeeinit spec.md and start implementing with TDD"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
š BusyBee
Autonomous TDD coding agent with pause/resume capabilities. A Claude Code plugin that implements features from specifications using test-driven development.
Overview
BusyBee is an MCP server that converts your specifications into a comprehensive feature list and autonomously implements each feature using TDD. It supports:
Multi-modal inputs: Files, text, images, URLs
Pause/Resume: Stop and continue work across sessions
Live status: Real-time progress monitoring
Web dashboard: Visual interface with state explorer
Git integration: Automatic commits after each feature
Installation
As a Claude Code Plugin
# Add from GitHub
/plugin install nonibytes/busy
# Or add from local path
/plugin install ./path/to/busyManual Setup
# Clone the repository
git clone https://github.com/nonibytes/busy.git
cd busy
# Install dependencies
pip install -e ".[dev]"
# Set OAuth token (required)
export CLAUDE_CODE_OAUTH_TOKEN="sk-ant-oat01-..."Quick Start
1. Initialize a Project
# From a spec file
/busybee:init spec.md
# From text instructions
/busybee:init "Build a todo app with user authentication"
# From multiple inputs
/busybee:init requirements.txt mockup.png "Add dark mode"2. Start Autonomous Implementation
/busybee:run3. Monitor Progress
# Check status
/busybee:status
# Open dashboard
/busybee:dashboard4. Pause/Resume
# Pause gracefully
/busybee:pause
# Resume later
/busybee:resume5. Update Requirements
/busybee:update "Add export to PDF feature"Commands
Command | Description |
| Initialize project with specifications |
| Start autonomous TDD implementation |
| Pause work gracefully |
| Resume from checkpoint |
| Show progress and status |
| Update requirements mid-flight |
| Open web dashboard |
Project Structure
After initialization, BusyBee creates a .busybee/ directory:
project/
āāā .busybee/
ā āāā feature_list.json # Source of truth (committed to git)
ā āāā state.json # Operational state (gitignored)
ā āāā history.jsonl # Activity log (gitignored)
ā āāā .gitignore
āāā ... your app code ...feature_list.json
The contract defining all features to implement:
[
{
"id": 1,
"category": "core",
"description": "User can log in with email",
"steps": ["Navigate to /login", "Enter email", "Click submit"],
"passes": false
}
]state.json
Current operational state (rebuilt on new machine):
{
"status": "running",
"current_feature_id": 45,
"progress": {"completed": 44, "pending": 156, "total": 200}
}history.jsonl
Append-only activity log:
{"ts":"2025-12-12T10:00:00Z","event":"init","details":"Created 200 features"}
{"ts":"2025-12-12T10:05:00Z","event":"feature_complete","id":1}Dashboard
The web dashboard provides:
Project list: All registered BusyBee projects
Progress view: Charts and statistics
Feature list: Filterable table of all features
Activity log: Recent events
State explorer: Raw JSON viewer for debugging
Access at http://localhost:8765 when running.
Architecture
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā Claude Code CLI ā
ā (invokes /busybee:init, /busybee:run, etc.) ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¬āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā MCP Protocol
ā¼
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā BusyBee MCP Server ā
ā āāāāāāāāāāāāāāā āāāāāāāāāāāāāāā āāāāāāāāāāāāāāā ā
ā ā MCP Tools ā ā Agent Core ā ā Dashboard ā ā
ā ā (7 tools) ā ā (SDK loop) ā ā (FastAPI) ā ā
ā āāāāāāāāāāāāāāā āāāāāāāāāāāāāāā āāāāāāāāāāāāāāā ā
ā ā ā
ā āāāāāāāāāāāāā“āāāāāāāāāāāā ā
ā ā State Manager ā ā
ā ā (JSON/JSONL files) ā ā
ā āāāāāāāāāāāāāāāāāāāāāāāāā ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāSecurity
BusyBee uses a project-scoped sandbox:
Write operations: Restricted to project directory only
Read operations: Allowed anywhere (for input files, images)
Command execution: Sandboxed within project
Authentication
BusyBee uses OAuth tokens (not API keys):
# Generate token
claude setup-token
# Set environment variable
export CLAUDE_CODE_OAUTH_TOKEN="sk-ant-oat01-..."Development
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Type checking
mypy src/busybee
# Linting
ruff check src/Based On
This project is inspired by Anthropic's autonomous-coding demo and the blog post Effective harnesses for long-running agents.
License
MIT
Related MCP Connectors
AI-powered spec-to-task decomposition and execution orchestration for coding agents.
Turn PRDs and product ideas into structured specs so coding agents build your intent, not theirs.
Writes adversarial test suites for AI-built code. Your agent's test engineer.
Project registry, behavioral specs, and engineering threads for AI coding agent workflows.