Similara startup that builds artificial intelligence agents for Mac OS and Windows, raised a $21.5 million series led by Felicis, with NVentures (Nvidia’s business arm), existing investor South Park Commons and others participating.
Simular is an interesting startup because unlike others, it doesn’t try to control the browser but the computer 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 click. So it’s more capable of doing, replicating any human activities in the digital world,” co-founder Ang Li told TechCrunch, offering the example of copying and pasting data.
On Monday it announced the release of version 1.0 for Mac OS. But it is also working with Microsoft to develop an agent for Windows. The startup is one of five agent 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 a timeline for the Windows version, Li was vague other than that it promises to be the same 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 expert Jiachen Yang. While their team has published its share of work, the work has not been strictly academic, Lee said. It was intended to improve Google products, including Waymo.
This AI product background is useful because, before the agency future of Silicon Valley’s dreams can be realized, there are many technical problems to solve. One of the biggest is that LLMs hallucinate a percentage of the time.
Agent tasks can require the completion of thousands to millions of discrete steps. Not only can a hallucination at any step invalidate all of the agent’s work, but hallucinations become statistically more likely as the number of steps increases.
One way to solve this is to make the “non-deterministic” LLM “deterministic”, meaning that instead of allowing the LLM to be endlessly creative, its responses or actions are scripted the same every time. But this risks limiting the entire creative problem-solving aspect of an agent.
Techcrunch event
San Francisco
|
13-15 October 2026
Simular marries the two. Its agent will freely iterate on the task, with the human user midway correcting, until the agent succeeds. The human is then locked into the workflow of that task, which makes it deterministic, repetitive.
“Our solution is, let the agents keep exploring the successful trajectory. Once you find a successful trajectory, it becomes a deterministic code,” Li explains.
The reason the startup can do this is because its work—which Li admits is still early days—isn’t just an LLM wrapper that sends and retrieves data to a model.
“We have a new technology that no other dealer company is using. We call it ‘neurosymbolic computer use agents’. It’s not completely LLM-based,” he said. “Our approach to solving hallucinations is to let LLM write code that becomes deterministic. So if you have a workflow that works, the next time we run the same workflow, it will also succeed.”
Another advantage is that this deterministic code that performs a repetitive task is in the hands of the end user and not the LLM. “Once they have the code, they can trust it, because they can inspect it, they can check it, they can see what’s going on,” Lee says.
Time will tell if this method is the magic that will put agents in the hands of every worker. Li says early beta customers include a car dealership that automates VIN number lookups and HOAs that extract contract information from PDF files. And the company open source project (currently only available for Mac OS) has led to automation ranging from content creation to sales and marketing.
Simular previously raised a $5 million seed round, bringing its total to around $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.
See the latest revelations on everything from agent AI and cloud infrastructure to security and more from Flags
