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

a2ui-project/a2ui

None observed · 2026-08-28

github.com/a2ui-project/a2ui · homepage · TypeScript · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

62/100

  • Activity 99
  • Release rhythm 35
  • Longevity 24

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 343
  • days_rel: n/a
  • days_push: 7
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

16210 stars · 1276 forks observed · 2026-08-28

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

A2UI is an open standard and set of libraries that lets AI agents generate rich, interactive user interfaces by sending declarative JSON component descriptions that clients render with their own native widgets (Angular, Flutter, Lit, etc.). It is designed to be secure (data, not executable code), LLM-friendly, and framework-agnostic, with renderers and transports like A2A included.

Use cases

  • let ai agents render interactive uis safely across trust boundaries
  • generate dynamic forms and cards from an llm agent
  • stream incrementally updatable ui from a chatbot
  • render the same agent ui payload on web, mobile, and desktop
  • build a custom component catalog for agent-generated interfaces
  • debug and preview agent ui json payloads

When to choose

  • you need agents to present rich interactive UIs instead of plain text
  • security matters and you cannot execute LLM-generated UI code
  • you want one agent UI format rendered across multiple client frameworks
  • you are building chat or agent clients with Angular, Flutter, or Lit

When to avoid

  • you need a fully stable, frozen specification (v1.0 is still a release candidate)
  • your UIs are static and don't need agent-driven generation
  • you need pixel-perfect control over rendering rather than a trusted component catalog
  • your stack has no supported renderer yet

Facets

framework · maturity active

ui-components frontend-framework agent-framework serialization rpc chat-interface artificial-intelligence frontend web-development large-language-models developer-tools cross-platform python agent-to-user-interface declarative-ui llm-generated-ui ui-protocol renderers flutter angular lit a2a-transport google ai-agents typescript nodejs web-server

4 sources

Member repositories

RepositoryRoleHealth v2
a2ui-project/a2uimain62

For agents

markdown · JSON · MCP: product_card(name="a2ui-project/a2ui")

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