mobilegym
by Purewhiter (personal account)
[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training (description from the project’s GitHub page)
Repository facts
- Stars
- 825
- Forks
- 140
- Open issues and pull requests
- 7
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- Purewhiter · Personal account
- Created
- May 14, 2026
- Last push
- Oct 9, 2026
Topics
Add this badge to your README
Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/github/purewhiter--mobilegym/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/github/purewhiter--mobilegym/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/purewhiter--mobilegym.svg" alt="Ranked #6,931 in AI on GitHub" height="20"></a>
Related projects
Projects that share this one’s GitHub topics.
Rank 8,856: facebookresearch/meta-agents-research-environments
Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces ev…
567 starsPythonMITLast push Sep 30, 2026
Rank 5,241: NVIDIA-NeMo/Gym
Evaluate and improve models and agents using environments
1,249 starsPythonApache-2.0Last push Oct 18, 2026
Rank 3,944: Core-Mate/OpenGUI
OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.
1,819 starsHTMLOther licenseLast push Oct 18, 2026
Rank 8,058: ServiceNow/AgentLab
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
655 starsPythonOther licenseLast push Oct 6, 2026
Rank 2,441: xlang-ai/OSWorld
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
3,217 starsPythonApache-2.0Last push Sep 14, 2026
Rank 5,850: JudgmentLabs/judgeval
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
1,068 starsPythonApache-2.0Last push Oct 18, 2026