TaskBoardAI logo

TaskBoardAI

by TuckerTucker

TaskBoardAI is a lightweight, file-based kanban board designed for AI Agents, including a web interface for Human-in-the-Loop (HIL) collaboration. It features JSON board files for full project context and an MCP Server for AI integration.

View on GitHub

Last updated: N/A

What is TaskBoardAI?

TaskBoardAI is a file-based kanban board system designed to be used by AI Agents and humans. It allows for the creation, management, and tracking of tasks and projects using a simple JSON format and a web interface.

How to use TaskBoardAI?

TaskBoardAI can be installed via npm or by cloning the repository. Once installed, you can create new boards, open existing boards, and start the MCP server for AI integration. The web interface allows for drag-and-drop sorting, adding/deleting cards and columns, and selecting available boards.

Key features of TaskBoardAI

  • Markdown Support

  • Subtasks

  • Tags & Dependencies

  • Drag and Drop

  • Next Steps

  • Webhooks

  • AI Integration

Use cases of TaskBoardAI

  • AI Agent task management

  • Human-in-the-loop collaboration with AI

  • Project tracking

  • Personal task management

  • Integration with other services via webhooks

FAQ from TaskBoardAI

Does TaskBoardAI have its own LLM integration?

No, TaskBoardAI does not have its own LLM integration. It is designed to be used with external LLMs or AI agents that can update the board context.

What is MCP?

MCP stands for Model Context Protocol. It is a protocol that allows you to create and manage boards using any tools supporting MCP (i.e. Claude Code, Cursor, Windsurf ... ).

How do I start the MCP server?

You can start the MCP server using the taskboard-mcp command if installed via npm, or ./_start_mcp if using the repository version.

Where are the board files stored?

When installed via npm, TaskBoardAI stores user data in ~/.taskboardai/ on Linux/macOS and C:\Users\<username>\.taskboardai\ on Windows. The boards/ directory contains your kanban board JSON files.

How do I integrate TaskBoardAI with other services?

TaskBoardAI supports webhooks for integrating with other services. You can create webhook configurations to trigger on events like board updates.