Ross ROSS = Recommend OSS · open-source software intelligence for agents

droidrun/mobilerun

Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖 observed · 2026-08-28

github.com/droidrun/mobilerun · homepage · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

86/100

  • Activity 99
  • Release rhythm 98
  • Longevity 36
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 3.0
  • age_days: 508
  • days_rel: 19
  • days_push: 8
  • n_releases_24m: 59

Full methodology

Adoption not part of the score

9127 stars · 980 forks observed · 2026-08-28

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

Mobilerun is an open-source Python framework for controlling Android and iOS devices with LLM-powered agents using natural language commands. It provides mobile-native tools for tapping, swiping, typing, and inspecting UI state, with a CLI, Python API, and an optional hosted cloud service.

Use cases

  • automate android apps with natural language commands
  • control an iphone with an llm agent
  • write mobile app tests in plain english instead of appium
  • scrape data from mobile apps without a public api
  • run multi-step workflows across mobile apps
  • give claude or cursor control of a real phone via mcp

When to choose

  • you need to automate tasks on real Android or iOS devices with an LLM agent
  • you want an LLM-agnostic framework where you can swap providers like OpenAI, Anthropic, Gemini, or Ollama
  • you want to self-host automation against your own device over adb
  • you need mobile app testing or data extraction without public APIs

When to avoid

  • you only need web browser automation rather than native mobile apps
  • you need a fully free solution and cannot afford LLM API costs or the hosted device cloud
  • you require deterministic, script-based mobile testing without LLM nondeterminism
  • your target platform is desktop or non-mobile

Facets

framework · maturity active

agent-framework workflow-automation llm-inference cli sdk mcp mobile-development large-language-models developer-tools python cli cross-platform mobile-automation android-automation llm-agent adb device-control ui-automation mobile-testing data-extraction ai-agents automation android ios

7 sources

Member repositories

RepositoryRoleHealth v2
droidrun/mobilerunmain86

For agents

markdown · JSON · MCP: product_card(name="droidrun/mobilerun")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem