Whiteboard is an open-source canvas for software design that lets AI coding agents draw diagrams directly onto a shared document through MCP. Built on a customized Code OSS base with an Electron desktop app, it combines prose, code peeks and sequence steps in one reviewable file. Agents such as Claude Code, Cursor and Codex connect over SSH and write to the canvas through session tools. A batch authoring mode runs the same pipeline headless in CI, so design reviews stay reproducible.
Be the first to rate Whiteboard. Your feedback helps other users decide.
Let Claude Code or Cursor sketch architecture and sequence diagrams straight onto the canvas
Show up to four code ranges inside a single review step for context
Run reviews headlessly in batch mode without the desktop app
Similar tools in the same category — compare side-by-side
Huzzah is an experimental editor that replaces longform chat prompts with persistent, declarative ps...
Needle 3 is a foundation model shipped as a single 8 to 29 MB binary for phones, wearables, robots a...
Copperhead is an open-source, verification-first AI agent for printed circuit board design, describe...
Guides and comparisons about code tools
Coding agents increased output but not shipped software. The gap is verification, context and drift. Here is what converts agent output into working systems.
A roundup of 18 AI tools launched between August and October 2026 that reached Hacker News front page: coding agents, guardrails, on-device models, dictation.
How development environments built around delegation differ from autocomplete-era assistants, and what Windsurf and Google Antigravity each do well.
What today's AI app builders can genuinely deliver — working full-stack applications from a description — and where they still hand the problem back to you.
How AI review tools differ from linters and from human reviewers, what they reliably catch, and how to add one without annoying your team.
