https://github.com/X-PLUG/MobileAgent

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family
https://github.com/X-PLUG/MobileAgent

agent android app automation copilot gpt4v gui harmony ios mllm mobile mobile-agents multimodal multimodal-agent multimodal-large-language-models

Last synced: about 1 month ago
JSON representation

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

• Host: GitHub
• URL: https://github.com/X-PLUG/MobileAgent
• Owner: X-PLUG
• License: mit
• Created: 2024-01-26T14:17:06.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-08-23T06:04:12.000Z (4 months ago)
• Last Synced: 2024-08-24T03:51:54.607Z (4 months ago)
• Topics: agent, android, app, automation, copilot, gpt4v, gui, harmony, ios, mllm, mobile, mobile-agents, multimodal, multimodal-agent, multimodal-large-language-models
• Language: Python
• Homepage: https://arxiv.org/abs/2406.01014
• Size: 33.7 MB
• Stars: 2,599
• Watchers: 43
• Forks: 233
• Open Issues: 26
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-ui-agents - code
• awesome-ui-agents - code
• awesome-LLM-resourses - MobileAgent
• AiTreasureBox - X-PLUG/MobileAgent - 12-20_3186_3](https://img.shields.io/github/stars/X-PLUG/MobileAgent.svg)|Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception| (Repos)
• StarryDivineSky - X-PLUG/MobileAgent - Agent是一个强大的移动设备操作助手家族，它通过多智能体协作实现高效的导航，支持多种移动设备操作，包括手机、PC 等。项目已在 NeurIPS 2024 和 ICLR 2024 Workshop on Large Language Model (LLM) Agents 等顶级会议上发表，并获得了 CCL 2024 最佳演示奖。用户可以通过 Hugging Face 和 ModelScope 体验 Mobile-Agent-v2 的演示，无需配置模型和设备即可立即体验。Mobile-Agent-v3 拥有更小的内存占用 (8 GB) 和更快的推理速度 (10s-15s 每操作)，并完全使用开源模型。 (A01_文本生成_文本对话 / 大语言对话模型及数据)
• alan_awesome_llm - MobileAgent
• alan_awesome_llm - MobileAgent