Novastart Builds Operating System for Concurrent AI Agents

Nov 6, 2026
Novastart offers an operating system where users can supervise up to 10 AI agents as they navigate applications, websites and shared workspaces.

Los Angeles software company Novastart is developing an operating system built for working alongside AI agents that navigate applications, interact with websites and complete tasks. Each agent gets its own cursor, keyboard and workspace, while the user keeps control of their own mouse and keyboard.

An infinite canvas replaces the traditional desktop. Novastart supports up to 10 concurrent AI agents, with a lead agent that can divide larger tasks among helpers, and all of their activity stays visible on the user's canvas. Teammates can join shared canvases and work in the same software.

"Computers were designed around the assumption that one person would be controlling everything," said Thomas Fraher, co-founder and CTO of Novastart. "We believe the operating system needs to evolve to support that."

Novastart supports more than 30 web applications as standalone windows, including Chrome, Claude, ChatGPT, Gmail, Excel, WhatsApp and Notion. It is available at novastart.com with Free, Pro and Team plans, as the Novastart App for Windows 10 or 11 and Intel-based Macs, or as Novastart OS for Intel and other x86 PCs via USB drive.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

Guide
Contract Lifecycle Management with AI

Contract Lifecycle Management with AI

Platforms where the assistant comes attached to the repository, the workflow and the approvals

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.