ProjectTodo: A local todo board with an MCP server for your AI assistant logo

ProjectTodo: A local todo board with an MCP server for your AI assistant

Show HN:ProjectTodo: A local todo board with an MCP server for your AI assistant

Visit Website
Related by shared tags and keywordsLeviathheadless-terminalToolbay Stack
show-hnAIaiai assistantautomation

Overview

ProjectTodo is a local to-do board designed for use by an individual and their AI assistant, running on the user's own machine. It consists of a single web page, a JSON file for storage, and an MCP server that allows AI assistants such as Claude Code or Claude Desktop to read and update the same to-dos. The server reads and writes whichever folders the user specifies, which is suitable for local use. Projects are displayed as cards on the first page, and each project can have its own board, timeline, lanes, current to-do, and documents. A project can be split into modules, each functioning as a sub-project with its own status and board. The board has lanes for Drafts, Current, Next, Done, and Later, and cards can be dragged between lanes. The timeline view shows dates along the top, with main to-dos spanning their days and packing into rows. Every change saves immediately and is visible to all open pages. The interface supports multiple themes and layouts, and is usable on a phone. The server requires Node 18 or newer and can be started with a script. The MCP server exposes tools such as get_playbook, list_projects, create_todo, and update_todo, and prompts like review_drafts and submit_draft. A PLAYBOOK.md file defines the workflow rules for the assistant, and the server sends a summary when a client connects.

Pricing

Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.

Visit Website

Prices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.

Use Cases

  • Individuals use ProjectTodo to keep a personal to-do board on their own machine.
  • Users connect their AI assistant to read and update the same to-dos they see.
  • Teams or individuals can commit the todos.json file to a repository to track project tasks.
  • Users can split a project into modules, each with its own board and timeline.
  • Assistants can review draft groups one at a time and submit them as planned to-dos.
  • Users can drag cards between lanes to change their status.
  • Users can view and edit to-dos on a timeline with dates and estimated durations.

Features

Keep todos on a local board

Share todos with an AI assistant

Organize projects into separate boards

Split projects into tracked modules

Drag task cards between status lanes

View dated tasks on a timeline

Save changes across open pages

Define assistant workflow in a playbook

Reviews

No reviews yet. Be the first to share your experience!

Rankings & collections