#8585th of 118 in Agent frameworks and SDKs
agenui
Native iOS, Android and HarmonyOS renderer for streamed A2UI generative UI
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 1.2k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- C++
54 on 21 Apr 20261,236 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AGenUI is a mobile SDK that implements Google's A2UI v0.9 protocol. A shared C++ core parses streamed LLM output, keeps a virtual component tree and diffs changes, and native renderers on iOS, Android and HarmonyOS draw 22 built-in components. It also ships a catalog JSON schema, an agent skill for generating A2UI messages, and a local bring-your-own-key studio.
Who it is for: Mobile developers rendering LLM-generated UI natively on iOS, Android, HarmonyOS
Strengths
- One C++ core shared across iOS, Android and HarmonyOS renderers
- Implements A2UI v0.9 with 18 protocol components plus 4 SDK extensions
- Custom component and function-call APIs let the LLM emit app-specific components
- Ships a freestanding catalog schema and an installable A2UI generation skill
Weaknesses
- Mobile only; no web or desktop renderer is mentioned
- Building from source needs Android Studio with NDK, Xcode with CocoaPods, or DevEco Studio
- Output quality depends on the LLM chosen; README only advises testing several models
- Chart, Markdown and Lottie components exist only in the playground, not the SDK
What it needs
- no GPU
- Needs Android Studio Hedgehog+, NDK 27.3.13750724, Xcode 15+, CocoaPods, CMake, DevEco Studio 4.0+, ohpm
- Models: DeepSeek, Qwen, GLM, OpenAI, Gemini
Quick answers
Is agenui open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does agenui need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 118| 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 | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |