Cursor

We're introducing Cursor Automations to build always-on agents.

Read more: cursor.com/blog/self-summ…

We trained Composer to self-summarize through RL instead of a prompt. This reduces the error from compaction by 50% and allows Composer to succeed on challenging coding tasks requiring hundreds of actions.

Learn more about building custom security agents: cursor.com/blog/security-…

We built a fleet of security agents to run continuously on our codebase. We're sharing new automation templates for you to do the same.

Learn more: cursor.com/blog/cursorben…

We use a combination of offline benchmarks and online evals to measure model quality. This makes results more useful, especially as public benchmarks are increasingly saturated.

We're sharing a new method for scoring models on agentic coding tasks. Here's how models in Cursor compare on intelligence and efficiency:

Access and manage project boards and tasks with the monday.com plugin.

View and manage issues, merge requests, pipelines, and repositories with the GitLab plugin.

Over 30 new plugins are now available on the Cursor Marketplace.

GPT 5.4 is now available in Cursor! We've found it to be more natural and assertive than previous models. It's currently the leader on our internal benchmarks.

Cursor can now continuously monitor and improve your codebase. Automations run based on triggers and instructions you define. cursor.com/blog/automatio…

We're introducing Cursor Automations to build always-on agents.

Cursor is now available in JetBrains IDEs through the Agent Client Protocol. cursor.com/blog/jetbrains…