meet your #robosecretary and #SaiFleet computers

Agent demos fooled you 👎 It trips, it asks for help, and somehow you're the one copying, pasting and running the commands. Meet your #Robosecretary. Meet your #SaiFleet. Sai brings state-of-the-art computer use to your own computer - your apps, your OS, in a floating window that leaves your mouse alone. Need more than one? Spin up to 100 cloud machines, each on the OS you pick, each on a different job. 100x the work, done without you. Sai. The autonomous computer fleet at your command. Free to start → sai.simular.ai

We told you what Sai can do. Now watch this. Live on Product Hunt today — don't forget to UPVOTE and leave a COMMENT ❤️ 🆙 producthunt.com/products/sim…

Presenting Sai World Where frontier computer-use technology meets the very human desire for breezier work (And to save tokens - our favorite feature of Sai)

Our head of research @xwang_lk joined Barry Barish, Terence Tao and other scientific visionaries at the @SAIRfoundation Science x AI Summit. Great conversations on open research, AI safety, agent market signals. And we're cooking something 🧑‍🍳

We are throwing a party during #SFTechWeek to nerd out on all things CUA 🖥️ ChatGPT Astra just pushed computer use agents back into the spotlight. But what needs to happen before CUA become ubiquitous? Simular is gathering folks who built agents at OpenAI and DeepMind, alongside a select group of researchers, investors and founders to debate the biggest questions in CUA today: reasoning, reliability, autonomy, economics. Could 2027 be the year computer-use agents reach AGI? Join us to find out at SF a16z @techweek_! partiful.com/e/YUKBbGuv0GuGM…

yes, you shouldn't have spent so much on tokens

The trajectories are also up on Huggingface huggingface.co/datasets/simu…

For everyone asking how we got 73% at 2/3 the cost: the full trajectories are now up on @huggingface huggingface.co/datasets/simu…

Give the Sai computer agent a try - get better results out of every dollar you spend 🫰sai.work?utm_source=x&utm_me…

Task #28: Vaccine booking This involves getting an email about required immunizations, a scanned vaccination record on the desktop, and a booking site with price, distance and date constraints. The requirements also state a Hepatitis B dose-spacing rule: dose 3 must come at least 16 weeks after dose 1 and at least 8 weeks after dose 2. The record shows three doses given 70 and 40 days apart, so a fourth booking is due. @sai_borg scored 1.0, Opus 4.7 scored 0.4, and Sol scored 0.0.

We challenged @sai_borg vs Opus vs GPT on tasks that we (humans) actually do in the real world. Task #68: The agents play Chrome Dino, a repetitive real-time game, and clear a score target on a live page. Scoring is pass/fail on the final score, and all three agents scored 1.0, so what actually separates them is the cost of getting there. Sai finished in 23 model turns, Sol needed 46, and Opus 4.7 took 201.

Our computer-use agent @sai_borg just beat Opus 5 and GPT-5.6 Sol on OSWorld 2.0. Sai scored 73% on the CUA benchmark where each complex task takes a skilled human over an hour to execute. And Sai did it at about 2/3 the cost per task of Opus and GPT 💸 The unlock is our neurosymbolic framework that pairs the exploratory power of neural networks with the logic of symbolic code, resulting in reliability and cost saving. Read the full report: simular.ai/articles/sai-tops…

Watch Sai-Fi & @sai_borg in action

Since our amazing intern published her open source CUA-on-smart-glasses project 'Sai-Fi', we've received lots of questions. So Jamie wrote this post to answer all the things you want to know about putting computer-use agents onto wearables. Read the full low down here: simular.ai/articles/why-type…

We are excited to speak at the @SAIRfoundation Science x AI Summit, co-founded by Barry Barish, Terence Tao and other scientific visionaries! The theme resonates with unified deep symbolic regression - harnessing the capacity of large neural models to ingest measured data and discover the underlying equations in compact and interpretable forms. Our Head of Research @xwang_lk will join a panel sharing how founders turn open problems into companies. At Simular, we advance neural-symbolic learning for computer agents, delivering 10x higher efficiency and better interpretability beyond pure LLM-based agents. The human practice of mathematics and theoretical science is the epitome of neuro-symbolic planning and learning: neural exploration generating knowledge in symbolic form. We look forward to the synergies at the summit - thanks to the organizers Chuck Ng, Samuel Pearton, and SAIR Caltech and the Merkin Center for Pure and Applied Mathematics. sair.foundation/events/scien…

We are excited to speak at the @SAIRfoundation Science x AI Summit, co-founded by Barry Barish, Terence Tao and other scientific visionaries! The theme resonates with unified deep symbolic regression - harnessing the capacity of large neural models to ingest measured data and discover the underlying equations in compact and interpretable forms. Our Head of Research @xwang_lk will join a panel sharing how founders turn open problems into companies. At Simular, we advance neural-symbolic learning for computer agents, delivering 10x higher efficiency and better interpretability beyond pure LLM-based agents. The human practice of mathematics and theoretical science is the epitome of neuro-symbolic planning and learning: neural exploration generating knowledge in symbolic form. We look forward to the synergies at the summit - thanks to the organizers Chuck Ng, Samuel Pearton, and SAIR Caltech and the Merkin Center for Pure and Applied Mathematics. sair.foundation/events/scien…

We’ve also open-sourced Sai-Fi: the Android app that brings the Sai voice concierge to Meta Ray-Bans. It’s not just a voice assistant. It’s an agent that runs on your actual machine, turning your glasses into a hands-free interface for real work. Check it out: github.com/simular-ai/sai-fi

We’re opening up the power of Sai to developers everywhere. With the new Sai API, you can integrate autonomous computer use directly into your own applications. Whether you’re building a workflow automation tool, a customer support bot, or a custom productivity suite, the Sai API gives you the ability to trigger real actions on real machines. Explore the documentation and start building: sai.work/api #SaiAPI #OpenSource #Automation #AI

Introducing Sai-Fi: an open source app that lets you talk to AI agent Sai through a pair of Meta Ray-Ban glasses. Sai is an autonomous computer-use agent. It can see the screen, move the mouse, type, and keep working even when you are away. We used Meta Ray-Bans for the first prototype but the glasses aren't really the point. Underneath is the Sai API and a voice concierge designed to work across different devices. The interface could live in an earpiece, a car, a small box on a workbench, or something nobody has built yet. Give it a microphone, a speaker, and a connection, and Sai has another way in. The bigger idea is an autonomous computer you can reach from anywhere. Bring @sai_borg to your own @Meta @ray_ban glasses today!