Hi, everyone.
I've been developing GemOS, a Gemini-exclusive personal AI assistant.
Most of the core features are now complete, and it's almost ready to meet the world!
Check it out: https://t.co/Pgi2m3tged
Introducing GemOS: a self-hosted AI assistant powered exclusively by Gemini 3.5 Flash.
It brings Hermes-style remote control to Google-native workflows, coding tasks, and long-running automation.
Plan tasks, ask for approval, use Google APIs, and execute from anywhere.
With Gemini 3.5 Flash, AI agents can multitask, understand context deeply, and generate creative solutions — powering smarter, autonomous workflows while staying fully integrated with Google services.
As a solo Google developer, I’m experimenting with a smart, autonomous AI agent — integrating official APIs and ready for long-term workflows.
You can think of it as a Hermes-style agent exclusive to Gemini 3.5 flash.
Gemini only.
Gemini 3.5 Flash delivers lightning-fast responses and high efficiency, enabling autonomous AI agents to handle complex workflows seamlessly. Ideal for developers seeking long-term, reliable AI support.
Watch how fast Gemini 3.1 Flash-Lite can generate websites. ⚡
This browser creates each page in real-time as you click, search, and navigate. Give it a try → https://t.co/h3W5o1wItY
Weather affects everything and everyone. Our latest AI model developed with @GoogleResearch is helping us better predict it. ⛅
WeatherNext 2 is our most advanced system yet, able to generate more accurate and higher-resolution global forecasts. Here’s what it can do - and why it matters 🧵
SIMA 2 🤝 Genie 3
We tested SIMA 2’s abilities in simulated 3D worlds created by our world model Genie 3.
It demonstrated unprecedented adaptability by navigating its surroundings and took meaningful steps toward goals.
Create an invitation right from your imagination 🪄
With video generation in the @GeminiApp you can turn simple descriptions into a high-quality, 8-second videos with sound effects and dialogue. You can even work off your own images¹ 🙌
1/ Some are saying they’ll always remember the day our Gemini 2.5 Flash Image (aka nano 🍌) was released - that was the biggest thing to happen on August 26th, right?:) Try it if you haven’t yet: https://t.co/z8moZCdxb8
More from an exciting week:
Yo, vibing with the Gemini Deep Research crew in NYC? Spilling tea on their epic category creation and that API? Spill more soon, or I’ll crash the next meetup!
Caught up with the Gemini Deep Research team in NYC, so cool to hear the story of how they created this category, the crazy product momentum, and what comes next. Stay tuned : )
And yes, we are working on the Deep Research API!
The plot thickens. 🕵️ Use Gemini 2.5 Pro in the @GeminiApp to turn random videos from your camera roll into a dramatic narrative.
Try it yourself:
1️⃣ Go to Gemini and select “2.5 Pro” from the model dropdown.
2️⃣ Tap the plus icon and upload three videos from your camera roll. (Pro/Ultra subscribers, try using your Veo creations! 🎥)
3️⃣ Ask Gemini to write a short story based on the videos. Here’s our prompt to get you started: “Come up with a premise for an epic adventure based on these videos.”
For developers, the command line interface (CLI) isn't just a tool; it's home. 🛠️
Transform your terminal with Gemini CLI: a free, open-source AI agent to help you get so many things done - from writing and understanding code to debugging issues and generating new apps. → https://t.co/K2ztZjl6ku
Introducing AlphaGenome: an AI model to help scientists better understand our DNA – the instruction manual for life 🧬
Researchers can now quickly predict what impact genetic changes could have - helping to generate new hypotheses and drive biological discoveries. ↓