#4141st of 82 in Agent frameworks and SDKs
openui
Generative UI framework that streams model-written UI via a compact language
- Stars
- 14.6k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
3,354 on 10 Apr 202614,598 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
OpenUI defines OpenUI Lang, a compact streaming-first language that models emit to describe UI, and renders it progressively as tokens arrive. You register a component library, generate a system prompt from it, and a renderer for React, Vue, Svelte or Angular draws the output. React also gets prebuilt chat layouts and two component libraries. The README reports up to 67% fewer tokens than equivalent JSON formats.
Who it is for: Frontend and agent developers adding model-generated UI to chat or copilot apps
Strengths
- Renderers for React, Vue, Svelte and Angular on a framework-agnostic core
- System prompt is generated from the component library you allow
- Benchmarked at 4800 tokens vs 10180 for Vercel JSON-Render across seven scenarios
- Scaffold CLI plus LangChain, assistant-ui and A2UI integrations
Weaknesses
- Prebuilt chat UI and component libraries ship for React only
- Requires adopting a new language that models must be prompted to emit
- Benchmark and comparison figures come from the project itself
- Hosted observability package depends on the Thesys console and gateway
What it needs
- no GPU
- Needs Node.js, LLM provider
- Models: unknown
Quick answers
Is openui open source?
Yes. Its code is on GitHub under the MIT license.
Does openui need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 82| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 90 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 89 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| #5 | tradingagentsMulti-agent LLM framework that simulates a trading firm's analysis process | 89 out of 100 |