# TencentQQGYLab/AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

Repository: https://github.com/TencentQQGYLab/AppAgent
Canonical: https://ross.abutalabs.com/products/appagent
Homepage: https://appagent-official.github.io/
Language: Python
License: MIT
License Family: permissive
Topics: agent, chatgpt, generative-ai, gpt4, gpt4v, llm
Last push: 2025-03-19T11:01:38+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 12, release rhythm 35, longevity 70
- inputs: {"age_days": 987, "days_push": 532, "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 6860, forks 760 (observed 2026-08-28T04:09:50.960362+00:00)

## What it is
AppAgent is an LLM-based multimodal agent framework that operates smartphone apps through human-like interactions such as tapping and swiping, using vision-language models like GPT-4V. It builds a knowledge base via autonomous exploration or observing human demonstrations, enabling task execution across diverse Android applications without system back-end access.

## Use cases
- automate tasks on android apps with an llm agent
- control a smartphone using gpt-4v vision
- build a gui agent that taps and swipes like a human
- let an ai agent explore and learn new mobile apps
- run smartphone app tasks from an android emulator
- test mobile app ui flows with an autonomous agent

## When to choose
- you want an open-source multimodal agent to operate android apps via the gui
- you need an agent that learns app navigation through exploration or human demos
- you want to research or extend llm-based smartphone automation

## When to avoid
- you need to automate ios or desktop applications
- you require system-level or back-end api automation rather than gui interaction
- you need a production-ready, fully supported product rather than a research framework

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, machine-learning, computer-vision, llm-inference, workflow-automation
- domain: artificial-intelligence, large-language-models, mobile-development
- platform: python, cross-platform
- tags: multimodal-agent, gui-agent, gpt4v, smartphone-automation, android, llm-agent, ui-automation, ai-agents, automation

## Member repositories
- TencentQQGYLab/AppAgent (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:50.960362+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 2026-08-29T17:41:43.226785+00:00, confidence not recorded.
  - readme: https://github.com/TencentQQGYLab/AppAgent (fetched 2026-08-28T04:09:50.960362+00:00, sha 0eff6aa307b6)
  - homepage: https://appagent-official.github.io/ (fetched 2026-08-29T08:37:37.397112+00:00, sha 4b9cbf1e922a)
- Data as of 2026-08-30T08:39:29.467469+00:00.