OpenUI
Thesys just open-sourced their generative UI rendering engine. Interesting timing given where Google a2ui and Vercel's json-render are headed. The difference worth noting: a2ui and json-render both treat JSONL as the contract between the LLM and the renderer. Thesys is betting that's the wrong primitive. Their engine uses a code-like syntax (OpenUI Lang) instead — LLM writes it, renderer executes it. The argument is that LLMs are fundamentally better at generating code than generating structured data, so you get cleaner output and ~67% fewer tokens. The broader vision seems to be a…
OpenUI launched on March 11, 2026 with 322 votes, #74 of 23,380 launches that month and more than 99% of that year's launches.
In plain words
OpenUI is an open standard that enables AI applications to generate interactive user interface components such as cards, tables, forms, and charts instead of plain text responses. It works with any AI model including GPT and Claude, as well as agent frameworks like ai-sdk and Google ADK. The standard is designed to be streaming-native and token-efficient, making it suitable for developers building AI-powered applications who want richer, more interactive user experiences.
written from the facts on this page · September 2026
From the sources
The Open Standard for Generative UIMake your AI apps respond with interactive UI components like cards, tables, forms and charts instead of text. Streaming-native, token-efficient, and works with any AI model (GPT,Claude,M2.5) and agent framework like ai-sdk, Google ADK
Full-stack, renderer-agnostic Generative UI with a streaming-first language, official React support, community integrations, and up to 67% fewer tokens than JSON.
Make your AI agents stream live charts, forms, cards, tables, and dashboards faster, with fewer tokens. Interfaces query your tools and MCP servers at runtime, so the data is always current. One response renders across React, Vue, Svelte, React Native, email, and script tags. UI renders progressively as the model responds, not after the full output. The model only composes your components and never runs arbitrary code. Build from the components and design system you already have. Make agent responses more reliable in production. Gateway catches and repairs invalid output before users see it. Chat Completions and Responses endpoints work with existing SDKs. Gateway switches providers if one…from openui.com
In the maker’s words, at launch
Hi HN, We made OSS Claude Cowork, built as an OpenClaw plugin. It lets you create live artifacts (like Claude) that connect to datasources instead of datasets. (eg: fetching Stripe data automatically) Other tools(Paperclip, Multica) focus on task management but our vision is to build one screen that feels like the…
Does a similar job
all alternatives →
Agents.json – OpenAPI Specification for LLMs2025 · github.com · ▲212Hey HN, we’re building an open specification that lets agents discover and invoke APIs with natural language, built on the OpenAPI standard. agents.json clearly defines the contract between LLMs and API as a standard that's open, observable, and replicable. Here’s a walkthrough of how it works: https://youtu.be/kby2Wdt2Dtk?si=59xGCDy48Zzwr7ND. There’s 2 parts to this: 1. An agents.json file describes how to link API calls together into outcome-based tools for LLMs. This file sits alongside an OpenAPI file. 2. The agents.json SDK loads agents.json files as tools for an LLM that…
- OSOpen-source Postman alternative with type safety2023 · recipeui.com · ▲275
Hello! This is Jeane and Samuel and we’re building RecipeUI. RecipeUI is an open source Postman alternative that uses TypeScript to statically type and autocomplete requests. We built this because current API tools don’t deal with the fact that some APIs are just painful to work with. For us, it’s usually error after error as we try to figure out how to properly form the first request. We recorded a demo to show you how TypeScript helps us autocomplete a request correctly. https://youtu.be/O_Mly_p-g5s How does our platform improve the developer experience? The analogy is…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Product Hunt launch ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
