# zai-org/Open-AutoGLM

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

Repository: https://github.com/zai-org/Open-AutoGLM
Canonical: https://ross.abutalabs.com/products/open-autoglm
Homepage: https://autoglm.z.ai/blog
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, phone-use-agent
Last push: 2026-03-06T08:38:39+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 70, release rhythm 35, longevity 19
- inputs: {"age_days": 268, "days_push": 180, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 26091, forks 4019 (observed 2026-08-28T04:11:38.830832+00:00)

## What it is
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
- artifact type: framework
- maturity: active
- function: agent-framework, machine-learning, computer-vision, llm-inference
- domain: artificial-intelligence, mobile-development
- platform: python, cli
- tags: phone-agent, adb, gui-automation, vision-language-model, multimodal, zhipu-ai, autoglm, ai-agents, automation, android

## Member repositories
- zai-org/Open-AutoGLM (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:38.830832+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:55:56.000312+00:00, confidence not recorded.
  - readme: https://github.com/zai-org/Open-AutoGLM (fetched 2026-08-28T04:11:38.830832+00:00, sha 23766dbce3ac)
- Data as of 2026-08-30T08:39:29.467469+00:00.