
Cursor announced version 2.0 of its AI-powered coding editor today, adding a multi-agent interface and the company’s first coding model.
“The first thing you’ll notice when you open Cursor is our new interface,” the Cursor team writes in the announcement post. “It’s more focused and designed from the ground up to be centered around agents rather than files. So you can focus on the outcomes you want while agents take care of the details. When you need to dive deep into the code, you can still easily open files in the new layout or switch back to the classic IDE.”
Cursor 2.0 includes two big new features:
Multi-agent capabilities. Cursor 2.0 supports running multiple AI agents in parallel without them interfering with each other. This feature can be powered by Git worktrees or remote machines, and it significantly improves the quality of the final output, Cursor says.
Composer. This is Cursor’s frontier model for low-latency agentic coding, and it’s four times faster than “similarly intelligent models.” Composer was trained with codebase-wide semantic search and other tools, which Cursor says make it much better at understanding and working in large codebases.
Cursor 2.0 is now available for download from the Cursor website.