When we started NeuralAgent back in April 2025 it was one of the first agents in the world that uses a user's personal computer, not a computer on the cloud, thats what made it to spread to 180 countries and tens of thousands of users in a short amount of time. Today, I am excited to announce that we are experimenting with something new, something called NeuralOS, it's the next evolution of the Neural experience. With NeuralOS, intelligence stops being an app you open and close and it becomes the OS itself, it becomes the computer itself, it's always on and always ready. Imagine for example you are now on the gmail interface, and you say 'Hey Neural, send a reply to John here', and it just understands, it just knows and in milliseconds types the reply, asks for your approval and then sends it. Or if you are on an interface and there was an error and you say "Hey Neural, fix this" and it just knows! It just works across any app, any screen, any interface, you call it via a keyboard shortcut or voice and ask it to do something, and it does it in milliseconds. Now that we have the Neural fast model, I feel now is the time for this experiment. Stay tuned for NeuralOS! It will be an OS layer that's always on that can run on Windows and macOS and soon Linux as well! As always, we would love to hear your feedback! Check out the NeuralOS demo video here:
I can't believe that this is in real time, I just can't believe it! NeuralAgent is using interfaces AT LIGHTNING SPEED. If you ever used Claude Cowork computer use or other computer use agents, you'd know how powerful this is! The video is in real time, it's at playback 1.0, no speeding at all, all computer use demos you were seeing were at least 8x speeded (including our own old demos)! And the task is: "Send a Whatsapp desktop message to Khalid Shadid about the future of AI, attach an image in the message from my downloads, it's a chatgpt generated image. GO!" Our fast model is now performing at its best ever in terms of speed and accuracy! It now checks its work while maintaining high speed! You must try it now, download NeuralAgent here: https://getneuralagent.com/downl...
Introducing NeuralAgent's fast computer-use model. In this example, NeuralAgent's fast model was given a task to go to NeuralAgent's Discord and send an announcement introducing itself as NeuralAgent's fast model controlling Khaled's computer and to write something exciting as well! It executed the task at lightning speed! Events in the video occur in real time!
Check out NeuralAgent 3.0 here: https://www.getneuralagent.com
Check out the NeuralOS Demo, Your Computer Just Knows you! With NeuralOS, Intelligence stops being an app you open and close, it becomes the OS itself, the computer itself. Stay Tuned!
Two of NeuralAgent's most powerful capabilities are UI Skills and Fast Skills and together, they represent a fundamentally new way for AI to interact with your computer.
UI Skills: Your AI Learns Any Interface
UI Skills are reusable knowledge packages that teach NeuralAgent exactly how to operate specific apps and websites. Instead of guessing where buttons are or struggling with unfamiliar interfaces, NeuralAgent loads a UI Skill and instantly knows the layout, workflows, and interaction patterns of any application.
Think of it like muscle memory for AI. Once a UI Skill is created either by the NeuralAgent team, the community, or yourself NeuralAgent can operate that interface reliably every single time. Browse the marketplace, install with one click, and your AI gains new capabilities instantly.
UPDATE: Fast just got even faster, we made it 2x faster than today's and yesterday's demos, it's a breakthrough! NeuralAgent's lightning-fast computer-use model in action! In this example, NeuralAgent's fast model was given a task to go to publish an X post. It executed the task at lightning speed! Events in the video occur in real time!
New in 3.0: our Lightning-Fast computer-use model. NeuralAgent sees your screen and controls your computer to get real work done, now powered by our Fast model that executes UI actions in ~285ms, alongside Fast Model Replays (save a task, re-run it in seconds) and Smart Model Routing. It plans, executes at high speed, and supervises itself for recovery. Desktop + browser. Windows + macOS. The fast model got even faster since we recorded the launch video, check out the comment below.
NeuralAgent 2.5 introduces Voice Mode, Watch & Learn, and Parallel Agents. Talk to NeuralAgent and it talks back, it listens, responds, and executes tasks without you touching the keyboard. Show it a task once and it saves it as a workflow it repeats any time. Spawn multiple agents working simultaneously, research 30 competitors at once, an hour of work in minutes. Combined with Workflows, @ Mentions, and a smarter memory system, this is the biggest update we've shipped.