Ross ROSS = Recommend OSS · open-source software intelligence for agents

thesysdev/openui

The Open Standard for Generative UI observed · 2026-08-28

github.com/thesysdev/openui · homepage · TypeScript · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

66/100

  • Activity 99
  • Release rhythm 35
  • Longevity 45

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 639
  • days_rel: n/a
  • days_push: 7
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

8463 stars · 612 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

OpenUI is an open-source, renderer-agnostic Generative UI framework built around OpenUI Lang, a compact streaming-first DSL that lets LLM agents compose interactive interfaces from your component library. It provides React SDKs, built-in component libraries, a streaming renderer, chat/agent interface surfaces, and developer tools, with integrations for LangChain, Vercel AI SDK, Mastra, and more.

Use cases

  • build a chat app where the LLM renders interactive dashboards and forms
  • let AI agents respond with UI components instead of plain text
  • stream generative UI from an LLM into a React frontend
  • create agent interfaces with artifacts like reports and slides
  • reduce token usage for model-generated UI compared to JSON
  • wrap my existing shadcn/ui or Material UI components for agent composition
  • connect LangGraph or Vercel AI SDK agents to a generative UI frontend

When to choose

  • you want LLM agents to render interactive, streaming UI in React
  • you need token-efficient structured UI generation with built-in component libraries
  • you want a production chat/agent interface with artifacts without building the shell yourself
  • you use agent frameworks like LangChain, Mastra, or Vercel AI SDK and need a UI layer

When to avoid

  • your app is not React-based (other framework support is community-maintained)
  • you need a simple static frontend with no LLM involvement
  • you want fully managed backend features without using OpenUI Cloud or self-hosting the backend layers

Facets

framework · maturity active

frontend-framework ui-components chat-interface agent-framework llm-inference data-visualization developer-tools artificial-intelligence large-language-models web-development frontend chatbots developer-tools cross-platform generative-ui streaming-ui dsl openui-lang react agent-interface mcp token-efficiency ai-agents nodejs web-server

8 sources

Member repositories

RepositoryRoleHealth v2
thesysdev/openuimain66

For agents

markdown · JSON · MCP: product_card(name="thesysdev/openui")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem