Rasul Osmanbayli retweeted
WAIT. YOU CAN GIVE AN AI AGENT YOUR IPHONE NOW? 🤯
Yep...and guess what..
4 minutes. EXACTLY.. that's it
From connecting my iPhone to the agent, giving it a prompt, to watching it complete the entire workflow....4 minutes.
Rasul Osmanbayli retweeted
YOUR AI AGENT CAN NOW CONTROL A REAL IPHONE.🔥
Just connect your iPhone to Mobilerun Cloud and let an agent control it with a single prompt.
Super simple setup.
Just an iPhone, a Mac or Linux, and under 2 minutes to get started.
Yes, you can even use Claude or Codex to run the automation😉.
Rasul Osmanbayli retweeted
Huge shoutout to the tech team @megauega, @nielsmdt99, Lucius, @Rasul_ for building such a great product. Proud of what we're creating together.
Rasul Osmanbayli retweeted
Copycats are popping up left and right across every industry.
Competition is great. It pushes the market forward.
Still waiting to see something that truly rivals @mobilerun_ai .
Rasul Osmanbayli retweeted
Most phone agents are tested in simulated environments, but the real world is messier: carts persist, listings change hourly, and navigation varies.
At @ScaleAILabs, we ran agents on real phones with real apps on AgentEnv Framework.
See more at agentenvframework.com/blog/a…
Rasul Osmanbayli retweeted
@elonmusk when can we provide you with the mobile runtime with our phone infra?
mobile-harness scored 100% on the AndroidWorld benchmark!
mobile-harness is a harness for agents like Codex, Claude Code, and OpenClaw that gives them better mobile controls, app cards, and persistent memory. The agents can learn from previous runs by reviewing what worked and what didn't, then updating their cards and memory for future tasks.
AndroidWorld consists of 116 tasks across 20 Android apps from everyday actions to workflows that involve several apps.
Rasul Osmanbayli retweeted
Mobilerun just beat GOOGLE’S ARTEMIS on AndroidWorld🤯🔥
116/116 tasks completed.
The benchmark spans 20 Android apps and tests agents on real, multi-step mobile workflows.
Google Artemis - 99%+
Mobilerun AI - 100%
Mobile agents are getting really good. And this is just the beginning.
Rasul Osmanbayli retweeted
Breaking: Mobilerun just beat GOOGLE’S ARTEMIS on AndroidWorld🔥
We ran the full benchmark and mobilerun completed 116/116 tasks with a full official score on Google's AndroidWorld benchmark, spanning 20 Android apps and multi-step workflows.
Google Artemis scored 99%+ and Mobilerun AI scored 100% on the same benchmark.
Rasul Osmanbayli retweeted
Book an Uber in 20 seconds⚡️
I finally got access to Jev, and the first thing I did was give it a phone.
It’s blazingly fast at executing actions.
At this point, the only bottleneck seems to be the UI animations themselves.
Rasul Osmanbayli retweeted
📱 iOS 27 is here, and mobilerun-ios v0.4.0 is built to make automating it much better.
Factory reset. Onboard. Automate. Record. Reset. Repeat.
Running your own iPhones with Mobilerun just got a lot easier. 🧵
Rasul Osmanbayli retweeted
Most outreach tools save you a few minutes.
This one saves you hours.
Tell your agent who to reach, what to say, and when.
You own the strategy.
It runs the whole thing end to end from a chat.
That’s it.
Rasul Osmanbayli retweeted
With Mobilerun, you can connect, stream, control, and automate your own physical iPhone.
The best part is that once it’s set up, you can connect it to Codex or Claude Code, or use the @mobilerun_ai Virtual Assistant to create workflows.
Rasul Osmanbayli retweeted
Mobile automation gets messy when every device workflow starts from scratch.
Mobilerun is an open-source framework for controlling Android and iOS devices with LLM agents.
It helps you automate mobile tasks from natural-language commands by giving agents tools to inspect UI state, understand screenshots, use gestures, and run workflows from a CLI or Python API.
Key features:
• Android and iOS control – use the Android Portal app or the separate iOS Portal flow to target mobile devices
• LLM-provider flexibility – supports listed providers including OpenAI, Anthropic, Gemini, xAI, Ollama, DeepSeek, OpenRouter, and compatible models
• Vision plus UI state – combines accessibility trees with screenshots for visual understanding
• Direct and reasoning modes – run straightforward tasks or enable planning for more complex multi-step automation
• Builder-friendly interfaces – automate from the CLI, a terminal UI, Docker, or Python code
It’s open-source (MIT license).
Link in the reply 👇
Rasul Osmanbayli retweeted
We just killed LinkedIn Helper🫡
tell the agent - message all my new LinkedIn connections with this pitch.
and the agent handles the outreach for you.
The best part is you can set it to run every day automatically.
Give it a try at cloud.mobilerun.ai/









