By acedusse (inspired by claude-task-master)

A task management system for AI-driven development with Claude, designed to work seamlessly with Cursor AI. Now with a comprehensive UI interface replacing the CLI experience!

Project Vision

Teamwork reimagines software development by providing a complete visual representation of the entire development cycle, from PRD to production. Our vision:

• Visual Task Management: Transform abstract task lists into intuitive visual workflows
• Complete Development Visualization: See the entire software development cycle in one unified interface
• AI Agent Orchestration: Control development through AI agents that handle implementation tasks
• Product Owner-Centric: Position the user as the Product Owner, focusing on vision and requirements while AI handles execution
• Human-AI Collaboration: Create a seamless workflow between human product vision and AI implementation capabilities

Project Status: Transitioning from CLI to UI

Teamwork is currently transitioning from a CLI-based tool to a full UI application with these key features:

• Complete UI interface replacing all CLI commands with intuitive visual interactions
• Express server backend handling all API requests and operations
• Modern frontend built with React and Material-UI with custom theming
• WCAG 2.1 AA compliant design with an earth-tone color palette
• Optimized for desktop use with comprehensive workflows for PRD upload, task management, and sprint creation

Requirements

Teamwork utilizes AI across several commands, and those require a separate API key. You can use a variety of models from different AI providers provided you add your API keys. For example, if you want to use Claude 3.7, you'll need an Anthropic API key.

You can define 3 types of models to be used: the main model, the research model, and the fallback model (in case either the main or research fail). Whatever model you use, its provider API key must be present in either mcp.json or .env.

At least one (1) of the following is required:

• Anthropic API key (Claude API)
• OpenAI API key
• Google Gemini API key
• Perplexity API key (for research model)
• xAI API Key (for research or main model)
• OpenRouter API Key (for research or main model)

Using the research model is optional but highly recommended. You will need at least ONE API key. Adding all API keys enables you to seamlessly switch between model providers at will.

Quick Start

Option 1: MCP (Recommended)

MCP (Model Control Protocol) lets you run Task Master directly from your editor.

1. Add your MCP config at the following path depending on your editor

Cursor & Windsurf (mcpServers)

🔑 Replace YOUR_…_KEY_HERE with your real API keys. You can remove keys you don't use.

VS Code (servers + type)

🔑 Replace YOUR_…_KEY_HERE with your real API keys. You can remove keys you don't use.

2. (Cursor-only) Enable Taskmaster MCP

Open Cursor Settings (Ctrl+Shift+J) ➡ Click on MCP tab on the left ➡ Enable task-master-ai with the toggle

3. (Optional) Configure the models you want to use

In your editor's AI chat pane, say:

Change the main, research and fallback models to <model_name>, <model_name> and <model_name> respectively.

Table of available models

4. Initialize Task Master

In your editor's AI chat pane, say:

Initialize taskmaster-ai in my project

5. Make sure you have a PRD (Recommended)

For new projects: Create your PRD at .taskmaster/docs/prd.txt
For existing projects: You can use scripts/prd.txt or migrate with task-master migrate

An example PRD template is available after initialization in .taskmaster/templates/example_prd.txt.

Always start with a detailed PRD.

The more detailed your PRD, the better the generated tasks will be.

6. Common Commands

Use your AI assistant to:

• Parse requirements: Can you parse my PRD at scripts/prd.txt?
• Plan next step: What's the next task I should work on?
• Implement a task: Can you help me implement task 3?
• Expand a task: Can you help me expand task 4?

More examples on how to use Task Master in chat

Option 2: Using Command Line

Installation

# Install globally
npm install -g task-master-ai

# OR install locally within your project
npm install task-master-ai

Initialize a new project

# If installed globally
task-master init

# If installed locally
npx task-master init

This will prompt you for project details and set up a new project with the necessary files and structure.

Common Commands

# Initialize a new project
task-master init

# Parse a PRD and generate tasks
task-master parse-prd your-prd.txt

# List all tasks
task-master list

# Show the next task to work on
task-master next

# Generate task files
task-master generate

Implementation Roadmap

The UI transition is being implemented on a two-week timeline with the following priorities:

1. Core Functionality: Converting all CLI commands to equivalent UI functionality
2. User Experience: Implementing interfaces for PRD upload, task/backlog generation, and sprint creation
3. Visual Design: Applying the custom Material-UI theme with earth tones and ensuring accessibility compliance
4. Integration: Connecting the Express backend with the React frontend

Future Roadmap

Our long-term vision includes:

1. Complete Visualization Layer: Interactive graphs and dashboards representing the entire software development process
2. AI Agent Framework: Infrastructure for AI agents to autonomously implement tasks based on Product Owner guidance
3. Human-in-the-loop Workflows: Streamlined processes for human review, feedback, and direction of AI-generated implementations
4. Product Owner Dashboard: Specialized views and controls for the Product Owner to guide development direction
5. Decision Support System: AI-powered insights and recommendations for product development decisions
6. Full Development Lifecycle Integration: Extending beyond task management to include planning, testing, and deployment phases
7. MCP Server Integration: Support for Model Context Protocol servers to enhance AI capabilities
8. A2A and AG2U Protocol Support: Implementation of Agent-to-Agent and Agent-to-User protocol standards for improved communication
9. Hybrid LLM Architecture: Integration with both Ollama and Huggingface to combine paid cloud LLMs with locally-run open-source models
10. AI Budget Optimization: Smart routing of requests between paid and local LLMs based on task complexity and resource requirements

Documentation

For more detailed information, check out the documentation in the docs directory:

• Configuration Guide - Set up environment variables and customize Task Master
• Tutorial - Step-by-step guide to getting started with Task Master
• Command Reference - Complete list of all available commands
• Task Structure - Understanding the task format and features
• Example Interactions - Common Cursor AI interaction examples
• Migration Guide - Guide to migrating to the new project structure
• Project Architecture - Overview of how the codebase fits together
• API Documentation - Extend Task Master programmatically
• Release Process - How versions and changelogs are managed

Troubleshooting

If task-master init doesn't respond:

Try running it with Node directly:

node node_modules/claude-task-master/scripts/init.js

Or clone the repository and run:

git clone https://github.com/eyaltoledano/claude-task-master.git
cd claude-task-master
node scripts/init.js

Contributors

Star History

Licensing

Task Master is licensed under the MIT License with Commons Clause. This means you can:

✅ Allowed:

• Use Task Master for any purpose (personal, commercial, academic)
• Modify the code
• Distribute copies
• Create and sell products built using Task Master

❌ Not Allowed:

• Sell Task Master itself
• Offer Task Master as a hosted service
• Create competing products based on Task Master

See the LICENSE file for the complete license text and licensing details for more information.