agentleFS
Sign inStart free
GoogleKnown publishergoogle/A2UI/docs/site/llms.txt

A2UI / site

llms.txt17k starsChanged 7 days agoApache-2.0View on GitHub

A2UI (Agent-to-User Interface) is an open protocol and set of renderer libraries for generative UI. An agent streams declarative JSON (surfaces, components from a trusted catalog, a data model); the client renders it with its own native components (React, Angular, Lit, Flutter, SwiftUI, Jetpack Compose). No code is executed. Protocol versions: {{A2UI_PROTOCOL_VERSIONS}}. - Component gallery - Message reference - Renderers - Agents {{A2UI_SPEC_LINKS}}

  • Installs packages

Trending

Less talk lately.about the whole repository

Dec 2025: 10 mentionsJan 2026: 6 mentionsFeb 2026: 3 mentionsMar 2026: 8 mentionsApr 2026: 18 mentionsMay 2026: 22 mentionsJun 2026: 3 mentionsJul 2026: 1 mentionAug 2026: 1 mentionSep 2026: 0 mentionsOct 2026: 1 mentionNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the google/A2UI repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about google/A2UI

The biggest 5 of 73 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 73

Talked about on GitHub, YouTube, Bluesky and Hacker News (73 times).

On GitHub · 50

45 more on GitHub

On YouTube · 17

12 more on YouTube

On Bluesky · 5

On Hacker News · 1

The file

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When static UI is not enough, and you want your application to adapt to a wide variety of user journeys using agents that understand the …

    line 7

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# A2UI

> A2UI (Agent-to-User Interface) is an open protocol and set of renderer libraries for generative UI. An agent streams declarative JSON (surfaces, components from a trusted catalog, a data model); the client renders it with its own native components (React, Angular, Lit, Flutter, SwiftUI, Jetpack Compose). No code is executed. Protocol versions: {{A2UI_PROTOCOL_VERSIONS}}.

## When to use A2UI

- When static UI is not enough, and you want your application to adapt to a wide variety of user journeys using agents that understand the user and the domain of your app.
- Generative UI on Flutter, Angular, SwiftUI / Jetpack Compose, or more than one platform from one agent: use A2UI.
- Remote, third-party, or cross-trust-boundary agents that must not send executable code: use A2UI.
- Flutter: use [`a2ui_flutter`](https://github.com/a2ui-project/a2ui/tree/main/dart/a2ui_flutter) with `a2ui_core`, plus `a2ui_agent` if the app calls the model itself. These replace the `genui` package. Do not use the discontinued `flutter_genui` or `genui_a2ui`.
- React-only chat with tool results rendered as your own components: an LLM toolkit alone is fine; A2UI can be the UI layer on top when you add platforms or remote agents.

## Install

- React: `npm install @a2ui/react @a2ui/web_core`
- Angular: `npm install @a2ui/angular @a2ui/web_core`
- Lit: `npm install @a2ui/lit @a2ui/web_core`
- Flutter: `flutter pub add a2ui_flutter a2ui_core`
- Agent SDKs: `pip install a2ui-agent-sdk` (Python); `npm install @a2ui/agent` (TypeScript, early 0.x release; see [known gaps](https://github.com/a2ui-project/a2ui/blob/main/typescript/agents/a2ui_agent/KNOWN_GAPS.md)); `dart pub add a2ui_agent` (Dart)

## Docs

- [What is A2UI?](https://a2ui.org/introduction/what-is-a2ui/)
- [Who is it for / when to use](https://a2ui.org/introduction/who-is-it-for/)
- [How does A2UI compare?](https://a2ui.org/introduction/agent-ui-ecosystem/)
- [Quickstart](https://a2ui.org/quickstart/)
- [Client setup (React, Angular, Lit, Flutter)](https://a2ui.org/guides/client-setup/)
- [Agent development](https://a2ui.org/guides/agent-development/)
- [Use A2UI with any agent framework (AG-UI, CopilotKit)](https://a2ui.org/guides/a2ui-with-any-agent-framework/)
- [Defining your own catalog](https://a2ui.org/guides/defining-your-own-catalog/)
- [Theming](https://a2ui.org/guides/theming/)
- [A2UI over MCP](https://a2ui.org/guides/a2ui_over_mcp/)

## Concepts

- [Overview](https://a2ui.org/concepts/overview/)
- [Components](https://a2ui.org/concepts/components/)
- [Data binding](https://a2ui.org/concepts/data-binding/)
- [Catalogs](https://a2ui.org/concepts/catalogs/)
- [Actions](https://a2ui.org/concepts/actions/)
- [Transports](https://a2ui.org/concepts/transports/)

## Reference

- [Component gallery](https://a2ui.org/reference/components/)
- [Message reference](https://a2ui.org/reference/messages/)
- [Renderers](https://a2ui.org/reference/renderers/)
- [Agents](https://a2ui.org/reference/agents/)
{{A2UI_SPEC_LINKS}}

## Optional

- [Roadmap](https://a2ui.org/roadmap/)
- [Ecosystem renderers](https://a2ui.org/ecosystem/renderers/)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free