We benchmarked our new rendering spec against @vercel json-render. 3× faster rendering. 67% fewer tokens. Far more reliable outputs. Meet OpenUI Lang, the open standard for generative UI. Try it today and star us on GitHub⭐️, link below.

Generative UI のためのフレームワーク OpenUI azukiazusa.dev/blog/openui-f…

Someone just open-sourced a new standard for AI-generated UI. OpenUI lets your LLM stream real components (charts, forms, dashboards) directly into React. No more parsing massive JSON blobs. → 67% fewer tokens than JSON → 4.9s render vs 14.2s for Vercel's approach → Web, mobile, and email support 100% open source.

huge congratulations to everyone who participated!! @tokensandai

Most debates about Generative UI are actually two decisions being confused as one. 1. Transport: where does the UI appear? (AG-UI for your app, MCP-Apps for ChatGPT/Claude) 2. Generation: what does the agent emit? (Static, Declarative, or Open-Ended) Any pairing is valid. Once you separate them, most disagreements dissolve. Wrote a full report covering the protocols, the formats, the token benchmarks, and everything you should consider before choosing your stack.

ever wondered how AI models become production-ready? this friday. come build with us master the tools, systems, and feedback loops that turn AI models into reliable agents. 💵 $40K in prizes (cash,credits, giftcards) 📅 June 12 · SF 🎟️ Teams of 4 max @awscloud @AnthropicAI @AirbyteHQ @GuildAI @truefoundry @composio @render @ClickHouseDB @fastinoAI

It's really great to see my project AI Native Dashboard get listed in OpenUI Projects. Thanks to @thesysdev team. It is really cool to explore UI generation using natural language

OpenUI by @thesysdev The Open Standard for Generative UI

guess what? we hit 6767 stars on github this morning! the clip attached was my genuine reaction when i found out

AI is becoming more visual, dynamic, and interactive. @thesysdev, one of six startups participating in our Spring 2026 Accelerator, enables AI applications to respond with interactive UI and rich artifacts like dashboards, charts, forms, slides, reports, and more.

A startup just dropped a free open-source spec that generates UI components with 67% fewer tokens than JSON. It's called OpenUI. One protocol. No SDK lock-in. No proprietary runtime. You plug it into any LLM and the model starts shipping clean UI instead of bloated JSON blobs. Every "AI generates UI" framework before this made you pick one trade-off. Spend the tokens and get rich components. Compress the output and lose half your interactivity. Skip the schema and ship broken renders. OpenUI does all of it inside a single open spec. Here's what makes it different from every LLM-to-UI pipeline that came before: → 67% token reduction vs JSON for the exact same rendered component, which means your bills drop by two-thirds on every UI generation call → Model-agnostic, works with Claude, GPT, Gemini, DeepSeek, Llama, anything that can output structured text → Component-first instead of element-first so the LLM thinks in buttons, cards, and forms instead of nested div soup → Streamable by design, components render as the tokens arrive instead of waiting for the full response → Framework-neutral output that compiles to React, Vue, Svelte, or plain HTML without rewriting the prompt → Built-in primitives for forms, charts, tables, modals, and dashboards so you stop reinventing the same 40 components every project → Type-safe schema that catches malformed LLM output before it ever hits the renderer → Zero runtime dependency, the spec is just text the model already knows how to produce Killed: $200/mo "AI UI builder" SaaS, every prompt-to-React wrapper sitting on top of a bloated JSON schema, the 4000-token system prompts trying to teach GPT what a button is. Works with every major LLM provider. No API key lock-in. No vendor. MIT License. 100% Opensource.

Generative UI: interfaces that build themselves, adapt to context, and turn AI models into real interactive products instead of just conversations. Wrote about why text alone is no longer enough: shorturl.at/EfcHU @thesysdev

OpenUI lets you define components from prompts and render them as the model streams. running a 4 person company where nobody has time for proper dashboards, this kind of prompt-to-UI feels like it could save us another hire we cant afford 🍜

AI can plan your trip. But somehow the result still looks like Flight A $450 Flight B $520 Flight C $610 A wall of text I wrote about 5 things that look terrible as plain text and how @thesysdev 's OpenUI fixes them. dev.to/shogun444/5-things-th…

i guess that's one way to use openui?

The next shift is generative UI - interfaces that adapt, compose themselves, and turn AI models into real interactive products instead of just prompts and responses. Wrote about why Gemma 4 needs more than chat here: shorturl.at/l42cA @thesysdev

¡Vercel ACABA DE SER SUPERADO en UI generativa! Acaban de benchmarkear el nuevo estándar abierto OpenUI Lang contra json-render de Vercel y los números son BRUTALES: ✅ 3X más rápido. ✅ 67% MENOS tokens. ✅ Mucho más confiable. REPOOO👇x.com/thesysdev/status/20317…

Integrating Open WebUI with OpenUI is actually easier to implement than you might think! Open WebUIとOpenUIの統合、実は思ったより簡単に実装できます！ 🔗 github.com/thesysdev/openweb…

「OpenUI」はAIアプリの返答をMarkdownやJSONではなく、自分たちのUIコンポーネントで返すためのOSSフレームワーク。 LLMに自由にHTMLを書かせるのではなく、許可したコンポーネントだけをOpenUI Langで組ませる設計になっている点がいい。ストリーミング、型付きprops、React rendererまで含めて、Generative UIを実装に落としやすくしている。 AIアプリのUIが「チャット欄＋カード」から先に進むとき、こういう層がかなり重要になる。

OpenUI、★6千超えで話題になってるんだな 「事前に作るUI」から「AIが必要な時に出す」へシフトって これ本気で来たら、生成AIの使い勝手がまた一段上がるよな

【速報】 「AIにUIを動的生成させる」ためのオープン標準が出てきた😳 名前は OpenUI、★6千超え。 何が変わるかというと👇 ・AIごとにバラバラだった「UI生成」の仕様を統一 ・1度書けばどのAIエージェントでも動くUIが作れる ・Generative UI（生成UI）の議論が一気に進む ・実装側もユーザー側も恩恵あり UIの未来は「事前に作る」から「AIが必要なときに出す」へ。 この分野、Antigravity あたりが本気で来てる前に押さえとくべきです。 github.com/thesysdev/openui