9+ hour, 32+ min ago   (1205+ words) On July 22, we launched Cursor Router with two new configurations, Auto Intelligence and Auto Balance. Since then, we have continued improving both modes as new models have arrived and our routing system has learned from more production traffic. Today, Auto…...

2+ day, 9+ hour ago   (1745+ words) MoK grew out of several earlier attempts to speed up the MoE layer. Over the past year, we wrote our own MXFP8 and NVFP4 training kernels and developed the "warp decode" approach for MoE inference. Second, the integrated Grace CPUs (the "G…...

1+ week, 9+ hour ago   (777+ words) When we decided to give cloud agents computers so they could test their changes, the first step was to make sure they were good at testing them in our own codebase. Getting our monorepo working for cloud agents taught us…...

2+ week, 3+ day ago   (1757+ words) Earlier this year, we ran experiments to test the limits of scaling agents to cooperate toward a goal. Our hypothesis was that this would unlock a new tier of task scale and complexity. The flagship project was a long-running swarm…...

1+ mon, 1+ week ago   (554+ words) Cursor is now available as a native iOS app in public beta, so you can build from anywhere. Until now, developers have worked around the limits of their local machines, keeping laptops half-open and caffeinated everywhere they go. With Cursor…...

1+ mon, 3+ week ago   (528+ words) Every product in Wayfair's catalog is described by structured "tags" describing materials, dimensions, color, and other attributes. Over 47,000 distinct attribute tags power search, filtering, recommendations, product placement, and advertising for tens of millions of products. Nick Coleman, a senior machine…...

1+ mon, 3+ week ago   (1294+ words) That recognition pushed us toward developing a "classifier" agent that would govern overall agent autonomy. We wanted it to be a small model, so that it stayed fast and inexpensive to run, while still making a nuanced judgment about whether…...

1+ mon, 3+ week ago   (264+ words) Today we're shipping our biggest set of improvements yet to Bugbot. Bugbot is now over 3x faster to run, 22% cheaper, and finds 10% more bugs per review. In practice, 90% of Bugbot runs now finish in under three minutes. A faster, less expensive,…...

2+ mon, 1+ week ago   (947+ words) Running multiple agents in parallel on a local machine quickly runs into constraints on local resources: each agent competes for the same compute and managing 10 in-flight tasks across separate terminals becomes its own job. "There are ways to parallelize agents…...

2+ mon, 2+ week ago   (162+ words) Gartner has named Cursor a Leader in the 2026 Magic Quadrant™ for Enterprise AI Coding Agents, with the furthest placement on Completeness of Vision. The next year of Cursor is about making that platform more intelligent, efficient, and flexible. We're focusing…...