Doop - Design with AI agents - live on the same canvas
by•
Doop is an infinite multiplayer canvas where AI agents design beside you. Claude, Codex and any MCP agent stream frames onto the canvas live, review each other's work, and share one memory of your decisions, design taste and context. Bring your own AI subscriptions, no platform tokens, no markup. Open source.
Replies
Hey Product Hunt! 👋
I built Doop because most design tools aren't built to work with AI agents like Claude Code or Codex as first class citizens. Syncing memory between agents and making they follow guidelines and decisions was super hard. So I decided to build Doop, an open source Claude Design and Paper Design alternative.
Doop is an infinite canvas where AI agents are real collaborators: you see their cursors, they stream designs frame by frame, they review each other's work, and they share one memory of your decisions, design taste and context.
A few things I care about:
Bring your own AI: connect the Claude or ChatGPT subscription you already pay for.
No platform tokens, no markup.
Any MCP agent can join a canvas: Claude, Codex, Cursor, OpenClaw…
Doop is open source
I'd love to hear what you'd have your agents design first. Ask me anything!
This is so cool! Can't wait to use it 🔥🔥
@harini_mukesh You can either use the deskop or the web app. And then you can just hook up your Claude Code or Codex subscription via MCP. Its pretty straight forward. Have you worked with Claude Code or Codex MCPs before?
Congrats on the launch! I've been using Doop to design ad creatives with Claude and it's great 👍
@timosterbuhr Ahh thats great to hear Tim :) Would love some feedback.
Looks amazing! Congratulations on the launch @kevin_goedecke!
shared memory across claude and codex is the part i want most, agents forgetting design decisions is the usual pain. is that memory a file in my repo or hosted?
@niveditha_patluri1 The design memory is stored in multiple ways, there's an editable markdown file that stores hard design rules (similar to DESIGN.md) and then there's also a knowledge graph under the hood that stores information and also design decisions and style preferences. We use Cognee for the memory database.