mrkeyoor.com_
Sun 13 Sept 10:52 UTC
AI Toolsevaluationupdated 13 Sept 2026

doop review

Doop is an open-source multiplayer design canvas where people and software agents can work on the same interface designs in real time. It solves the awkward handoff between an AI generating markup and a designer repeatedly refreshing a separate preview.

trackingstars / 7d
Verdict

Our build completed in 13 seconds, and 350 of 361 tests passed while 11 were skipped. Doop is worth trying if live, inspectable collaboration between designers and MCP-connected agents is the actual requirement, not just an AI label on a drawing tool. Its recent v0.4.0 release and September 12 push show momentum, but the young codebase, AGPL-3.0 license, and operational choices around authentication, databases, and model accounts make it a measured pilot rather than an automatic production standard.

We ran it

Install✓ · 38s1867 packages · 569 MB
Build✓ · 13s
Tests✓ · 68s350 passed · 0 failed · 11 skipped of 361 (vitest)
Repo294 files~40,621 lines of source · 4 MB · 5 CI workflows · Dockerfile · tests dir

Answers from our run

Does doop build from source?

Dependencies installed in 38 seconds (1867 packages), and the build succeeded in 13 seconds. We cloned commit b187ba9 into a clean Debian container with 3 CPUs and no project-specific setup.

Do doop's tests pass?

Yes: 350 of 361 passed when we ran the project's own test command (vitest). Some failures need services or credentials a bare container does not have.

Who should not use doop?

Teams that need a long-established, enterprise-proven design platform

What are the alternatives to doop?

Penpot, Excalidraw, tldraw. Our build completed in 13 seconds, and 350 of 361 tests passed while 11 were skipped.

Setup4/5Quickstart worked, but 1,867 packages make it a heavy install
Docs4/5Clear local, Docker, MCP, auth, and provider setup guidance
Community3/5668 stars and fresh activity, but still a young project
Maturity3/5Solid tests and deployment paths, with 11 tests skipped

Who it’s for

Product teams that want humans and AI agents working on one live canvas
Claude Code users who want design tools exposed through MCP
Teams willing to self-host an AGPL-3.0 collaboration service
Small groups that need HTML-based frames, comments, presence, and design memory

Who it’s NOT for

Teams that need a long-established, enterprise-proven design platform
Organizations that cannot accept AGPL-3.0 obligations
Designers expecting a conventional vector editor with a mature plugin ecosystem
Operators who want advanced AI features without managing model credentials and provider choices

Setup reality

In our run, installation succeeded in 38 seconds with 1,867 packages and consumed 569 MB, the build succeeded in 13 seconds, and Vitest finished in 68 seconds with 350 passing, 0 failing, and 11 skipped tests out of 361. That is strong evidence that the quickstart is credible on a fresh Node 22 container, although the dependency footprint is substantial and the skipped tests still deserve inspection. The zero-configuration PGlite path looks appropriate for evaluation, while a serious deployment adds a real Postgres database, an authentication secret, and whichever provider credentials its AI features require.

Doop puts the agent on the canvas, not behind a prompt box

Doop is an open-source design workspace built around a specific idea: people and software agents should edit the same canvas and see the same state as work happens. Each Canvas has shareable Frames that render real HTML inside sandboxed iframes. The project says collaborators can see cursors, presence, edits, agent status, and an activity feed in one WebSocket room. At v0.4.0, this is more concrete than a chat panel that generates a static mockup and asks the designer to refresh.

The built-in MCP server is the most distinctive piece. A Claude Code user can connect with 1 command, approve the standard OAuth flow, and then ask the agent to work on a particular canvas. The agent acts with the permissions of the approving user, while the browser shows its progress. That model makes the output visible and attributable. It also makes Doop relevant to teams already using MCP clients, rather than forcing them into a proprietary prompt interface.

Our clean install, build, and test run all completed

We cloned commit b187ba9 into a fresh, unprivileged Debian container with 3 CPUs, 8 GB of RAM, Node 22, and no secrets. Installation succeeded in 38 seconds. Bun installed 1,867 packages and used 569 MB on disk, which is a sizable dependency footprint for a repository measuring 294 files, roughly 40,621 source lines, and 4 MB checked out. The quickstart was not merely plausible on paper, it worked on our box.

The build then succeeded in 13 seconds. Vitest completed in 68 seconds with 350 tests passing, 0 failing, and 11 skipped out of 361. We also found 5 CI workflow files, a Dockerfile, a compose file, and a tests directory. Those are useful production signals, but skipped tests are not passed tests. A team evaluating Doop should inspect what those 11 cases cover before mapping our clean result to its own authentication, WebSocket, storage, and provider configuration.

The local path is unusually considerate

The README offers 2 credible starting paths. For development, bun run dev starts the web app on port 4300 and the API, WebSocket, and MCP server on port 4400, with PGlite persisting data under data/pg. For a production-style start, Docker Compose runs the application with Postgres on port 4400 after an operator supplies BETTER_AUTH_SECRET. Optional SMTP, stock-photo, object-storage, and analytics integrations are described as graceful additions rather than prerequisites.

That separation gives evaluators a fast route without pretending that an embedded database is the final answer for every deployment. The non-Docker production path, bun run build && bun run start, serves the application from 1 server and accepts DATABASE_URL for Postgres. Still, our 569 MB install is heavy, and the real deployment surface extends beyond whether the process boots. Operators must plan authentication secrets, persistence, backups, reverse proxying, email delivery, and any external integrations they enable.

Live collaboration is the strongest reason to choose it

Doop's feature list hangs together around collaborative work rather than disconnected AI tricks. Frames are HTML artboards, comments can be pinned to elements, undo and redo are shared workspace concerns, and agents expose working status while streaming changes. The design-memory layer adds another useful loop: users can pin exemplar frames, record decisions, and let a distiller propose lasting style rules. The first-canvas performance is honestly labeled as a scripted replay in server/demo.ts, which replays 1 pre-authored frame rather than presenting it as autonomous intelligence.

The built-in design team can pick up a queued card, respond to an @mention, or process task feedback. Roles cover building plus focused passes such as UX, copy, brand, and accessibility, and a card can pass through several roles in order. The server-funded path uses Anthropic by default, with Azure OpenAI available as a server-level provider. After the configured free-task limit, users can connect either a ChatGPT subscription or an OpenAI API key and select among 3 documented tiers: gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna.

Credentials, licensing, and youth are real tradeoffs

AGPL-3.0 is another deliberate constraint, not a footnote. It can be a good fit for organizations comfortable contributing changes under that license, but legal review is sensible before modifying and serving the software. Maturity also needs perspective: the repository had 668 stars and 17 open issues in the supplied snapshot, its latest release was v0.4.0 on September 10, 2026, and its last push was September 12. Those dates indicate active development, while the low version number and recent creation signal a product still moving quickly.

Community momentum is promising, not yet conclusive

Fresh code activity and a release only 3 days before this review are healthier signals than an old tag viewed alone. The repository exposes contribution guidance, CI badges, and a Discord link, and the measured 5-workflow CI setup suggests maintenance discipline. However, 17 open issues do not tell us response time, maintainer capacity, or how quickly regressions are resolved. The available community notes include a Product Hunt discussion and a velocity snapshot, but not enough detailed user reports to support claims about broad production adoption.

It belongs beside design and development workflows

Doop fits best as the shared visual surface between a product team and its coding agents. The browser is where people review frames, comments, presence, and decisions; MCP is how an external agent participates; Postgres is the durable store for a serious deployment; and model providers power the optional resident team. It does not replace source control, CI, product analytics, or a full delivery pipeline. A sensible 1-team pilot would test access inheritance, concurrent edits, agent attribution, recovery, backups, and export or handoff expectations before expanding access.

Choose Doop when live, visible agent work is better than copying generated markup between tools. Choose Penpot for conventional design, Excalidraw for collaborative sketching, or tldraw for an embeddable canvas. Our successful 119-second install, build, and test sequence earns Doop a serious pilot.

Alternatives

ProjectWhat it isPick it when
Penpot gh↗An open-source design and prototyping platform built around standard web concepts.Pick this instead when conventional interface design and prototyping matter more than live agent participation.
Excalidraw gh↗A collaborative open-source whiteboard with a deliberately hand-drawn visual style.Pick this instead when your team mainly needs fast diagrams, sketches, and workshops.
tldraw gh↗An infinite-canvas SDK and collaborative drawing application for web products.Pick this instead when you want to build a custom canvas experience rather than adopt a complete agent design workspace.

What people are saying

  1. [producthunt] Doop
  2. [velocity-scout] kgoedecke/doop

Sources

  1. Doop GitHub repository
  2. Doop homepage

More ai tools reviews

agent-native · YuE · kserve · garak · reference-video-director · keras · the whole board →