Simulars AI agent wants to run your Mac, Windows PC for you | TechCrunch

Simular, a startup building AI agents for Mac OS and Windows, has raised a $21.5 million Series A led by Felicis, with NVentures (Nvidia’s venture arm), existing seed investor South Park Commons, and others joining in.

Simular is an interesting agentic startup because unlike others, it isn’t trying to control the browser but the PC itself.(Agentic AI refers to systems that can autonomously complete complex tasks with minimal human intervention.) “We can literally move the mouse on the screen and do the click. So it’s more capable of doing, repeating whatever human activities in the digital world,” co-founder CEO Ang Li told TechCrunch, offering the example of copying and pasting data into a spreadsheet.

On Monday it announced the release of its 1.0 version for Mac OS. But it’s also working with Microsoft to develop an agent for Windows. The startup is one of five agentic companies accepted into the Windows 365 for Agents program Microsoft announced in mid November. (The others are Manus AI, Fellou, Genspark, and TinyFish.) As for the timeline for the Windows version, Li was vague except to say it promises to be as or more popular than the Mac version.

Another reason to watch Simular is the bona fides of the founders: Li is a continuous learning scientist who previously worked at Google’s DeepMind, where he met his co-founder, reinforcement learning specialist Jiachen Yang. While their team published their fair share of papers, the work wasn’t strictly academic, Li said. It was intended to improve Google products, including Waymo.

That AI product background is helpful because, before the agentic future of Silicon Valley’s dreams can materialize, there are a host of technical problems to solve.One of the biggest is that LLMs hallucinate some percentage of the time.

Agentic tasks can require completing thousands to millions of discrete steps. Not only can a hallucination at any single step invalidate all of the agent’s work, but hallucinations become statistically more likely as the number of steps grows.

One way to solve this is to make the “non deterministic” LLM “deterministic,” meaning instead of allowing the LLM to be endlessly creative, its responses or actions are scripted the same each time.But that risks limiting the whole creative problem-solving aspect of an agent.

Simular is marrying the two. Its agent will iterate freely on the task, with the human user in the middle course correcting, until the agent achieves success. Then the human locks in that task’s workflow, which makes it deterministic, repeatable.

“Our solution is, let agents keep exploring the successful trajectory. Once you found a successful trajectory, that becomes deterministic code,” Li explains.

The reason the startup can do this is because its work — which Li admits is still early — is not just an LLM wrapper that sends and retrieves data to a model.

“We have a new technology which is not used by any other agent company. We call it ‘neuro symbolic computer use agents.’ It’s not fully LLM-based,” he said. “Our approach to solve hallucinations is to let the LLM write code which becomes deterministic. So if you have a workflow that works, the next time we run the same workflow, it’ll be successful as well.”

Another benefit is that this deterministic code that performs a repeatable task is in the hands of the end user, not the LLM. “Once they have the code, they can trust it, because they can inspect it, they can audit it, they can see what’s going on,” Li says.

Time will tell if this method is the magic that will bring agents into the hands of every worker. Li says his early beta customers include a car dealership automating VIN number searches, and HOAs extracting contract information from PDFs. And the company’s open source project (available only for Mac OS at the moment) has led to automations ranging from content creation to sales and marketing.

Simular previously raised a $5 million seed, bringing its total raised to about $27 million. Other investors in the company include Basis Set Ventures, Flying Fish Partners, Samsung NEXT, Xoogler Ventures, and podcaster and angel investor Lenny Rachitsky, the company says.