C

ClawGUI

Full-lifecycle GUI agent framework: train, benchmark, and deploy on mobile

PriceOpen Source (Apache 2.0)Reviewed2026-04-28
Verdict — Ship
3 Ships1 Skips
Visit github.com

The Panel's Take

ClawGUI is an open-source unified framework from Zhejiang University for building GUI agents — the kind that can control Android, iOS, and HarmonyOS apps through natural language. It covers the entire lifecycle: training via reinforcement learning (ClawGUI-RL), standardized evaluation across 6 benchmarks and 11+ models (ClawGUI-Eval), and production deployment across 12+ chat platforms (ClawGUI-Agent). The RL module uses parallel Docker-based Android emulators with GiGPO+PRM for fine-grained step-level rewards — a training setup that previously required significant infrastructure to replicate. The April 2026 release includes ClawGUI-2B, a 2-billion parameter agent that achieves 17.1% on MobileWorld benchmarks versus an 11.1% baseline. Weights are on HuggingFace and ModelScope. GUI agents are one of the most commercially valuable and technically unsolved problems in AI right now — every enterprise workflow that lives in a UI is a potential target. ClawGUI gives researchers and small teams the tooling to compete in this space without building the scaffolding from scratch. The 95.8% benchmark reproduction accuracy is particularly noteworthy for a research framework.

Share this verdict

ClawGUI verdict: SHIP 🚀

3 ships · 1 skip from the expert panel

Full review: shiporskip.io/tool/clawgui-gui-agent-framework-train-eval-deploy-2026

Weekly AI Tool Verdicts

Get the next verdict in your inbox

7 critics review a new AI tool every day. Weekly digest — free.

Embed this verdict

Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.

Ship · 7.5/10
HTML badge
<a href="https://shiporskip.io/api/badge-click/clawgui-gui-agent-framework-train-eval-deploy-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/clawgui-gui-agent-framework-train-eval-deploy-2026" alt="ClawGUI Ship verdict on ShipOrSkip" width="360" height="90" /></a>
Markdown badge
[![ClawGUI Ship verdict on ShipOrSkip](https://shiporskip.io/api/badge/clawgui-gui-agent-framework-train-eval-deploy-2026)](https://shiporskip.io/api/badge-click/clawgui-gui-agent-framework-train-eval-deploy-2026)
Iframe widget
<iframe src="https://shiporskip.io/embed/clawgui-gui-agent-framework-train-eval-deploy-2026" title="ClawGUI ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>

The reviews

The Docker-based Android emulator cluster for RL training is the part I've been trying to build myself for months. Having ClawGUI-RL handle the parallelization and reward shaping out of the box saves weeks of infrastructure work. The 2B model weights on HuggingFace make it immediately usable.

Helpful?

17.1% success rate on MobileWorld is progress, but it's still far from production-ready for anything critical. GUI agents break on UI updates, localization changes, and any element the training data didn't cover. This is research-grade, not deployment-grade — yet.

Helpful?

Every app that hasn't yet built an API is a target for GUI agents. ClawGUI is building the infrastructure layer that makes this tractable for more than just well-funded labs. The multi-OS support (Android + iOS + HarmonyOS) is a signal that the Chinese developer ecosystem is taking this seriously.

Helpful?

The 12+ chat platform deployment support means you could control mobile apps from Telegram or Discord. For creators automating social media workflows, content scheduling, or cross-app tasks, this is a framework worth watching closely.

Helpful?

Bookmarks

Loading bookmarks...

No bookmarks yet

Bookmark tools to save them for later