zai-org/Open-AutoGLM

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

26091 stars · 4019 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Open-AutoGLM is an open phone agent model and framework built on AutoGLM that understands phone screens multimodally and automates Android device tasks via ADB. Users describe goals in natural language, and a vision-language model (AutoGLM-Phone-9B) perceives the screen, plans actions, and executes them with human takeover for sensitive steps.

Use cases

• automate android phone tasks with natural language commands
• control a phone remotely over wifi adb
• build a phone-use ai agent
• automate app interactions on android with a vision language model
• test mobile apps with ai-driven ui automation
• run an ai assistant that operates my phone screen

When to choose

• you want an open-source phone-use agent for Android with a dedicated 9B vision-language model
• you need natural-language-driven automation of Chinese or multilingual mobile apps
• you want ADB-based device control with human takeover for logins and sensitive actions

When to avoid

• you need iOS automation without third-party integrations like Midscene.js
• you only need simple scripted UI tests without an LLM
• you require a fully hands-off agent with no human confirmation steps

Facets

framework · maturity active

agent-framework machine-learning computer-vision llm-inference artificial-intelligence mobile-development python cli phone-agent adb gui-automation vision-language-model multimodal zhipu-ai autoglm ai-agents automation android

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zai-org/Open-AutoGLM")