Design and diagrams decision
Brono
A technically capable person can build a narrower replacement (prompt→screen, Figma export, basic audit/heatmap) in multiple weeks, but Brono's proprietary trained engines, MCP integration claims, and enterprise features make a full replacement impractical for one developer to reproduce cheaply.
Visit website↗$8/mo
$96/yr
Read off the official pricing page.
$100one-off136 h to build
$100/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 14 seats.
The code exists. It is not what you are paying for.
These 2 projects are real, published, and do the core job — and this page still says keep paying. What the subscription buys is integration maintenance and proprietary models, and none of that ships in a repository. Fork one anyway if you want to. Go in knowing what it does not carry. What stays hard ↓ · All Brono alternatives, with the arithmetic →
What a replacement has to do
- Accept a text prompt or uploaded screen, generate a structured UI layout and high-fidelity screen assets using models, run automated accessibility and UX audits and a predictive heatmap, allow minor edits in a web editor, and export the result to Figma.
What it still won’t have
- Custom trained audit & design engine tuned to a company design system
- Deep MCP integrations and plug-and-play connectors mentioned on the site
- Enterprise features (SSO/SCIM, dedicated infra, SLA)
- Polish, reliability, and UX of the vendor-hosted studio
- Predictive heatmap quality from a proprietary model and ongoing model improvements
What remains hard
- Integration maintenance
Brono MCP lets you do everything Brono is an MCP server your AI tools connect to. Claude, Cursor, VS Code, Warp, ChatGPT, Antigravity, Bolt, Cluely, Lovable, Ghostty they all plug straight into Brono to generate, audit, and export designs f
- Proprietary models
Custom Audit & Design Engine (trained on your design system)
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 14 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal AI design studio using Node.js + React (Vite) + Postgres + Docker. Core features in scope: 1) REST endpoint accepting a text prompt and returning a structured UI JSON (implement using an LLM API to produce layer JSON and an off-the-shelf image/layout model for assets); 2) map UI JSON to Figma file format and implement Figma export using the Figma REST API; 3) run accessibility/UX audit checks (contrast, missing alt text, heading hierarchy) producing suggestions; 4) generate a predictive heatmap by integrating an open-source saliency model and overlaying results on the screen preview; 5) a simple React web UI to display generated screens, allow inline edits to text and images, save projects to Postgres, and authenticate users via OAuth; 6) implement credit accounting per generation. Out of scope: enterprise SSO/SCIM, custom-trained design engines, MCP plumbing, and advanced parallel generation. Include error handling, input validation, basic unit tests for server endpoints, and Docker compose for local dev.
How we checked
How the score was reached
- Pay verdict base20
- An open-source build was found+5
- 3 cited sources+3
- Price verified on pricing page+3
- Hard moats found in the evidence-3
- Evidence score28
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 3
Every page the run actually retrieved.
- official productBrono homepage (pricing & product)
- open sourcenexu-io/open-design
- open sourceOpenCoworkAI/open-codesign
Integrity checks
What held up, and what did not.