Cursor now supports Agent Plugins, an open standard for bundling skills and MCP servers for use across agents.
Cursor Router keeps improving from millions of in-product user interactions each week.
We intelligently classify and route requests, lowering latency and reducing cost based on the task.
Show more
We're open-sourcing Mixture-of-Kittens (MoK), our MoE training megakernel for NVL72s.
It fuses all Mixture-of-Experts communication and computation into a single, fully deterministic kernel, and runs up to 2.37x faster than the strongest public baselines.
Show more
Cursor can now read, write, and act across your Google Workspace.
New plugins give agents direct access to Gmail, Google Drive, Calendar, Docs, and Sheets.
Cloud agents are now 20-30% more token efficient, and 80% more efficient on runs with computer use.
We've improved how they handle MCPs, skills, and computer use, so you can delegate more ambitious tasks and get back demos while staying within budget.
Show more
It’s now easier to move local agents to the cloud so they can keep working with your laptop closed.
Prompt Cursor from your phone, run many agents in parallel, and get back PRs with demos of their work.
Show more
Cursor is now on iPad.
All the power of Cursor on iPhone, with more room to work with agents.
Today we're launching Cursor Start, a new ₹649/month plan for developers in India.
Start includes generous access to Grok 4.5 and Composer, so you can plan, build, test, and ship with agents every day.
Show more
Kimi K3 is now in Cursor! It scores close to the frontier on CursorBench.
It's available on US-based inference thanks to our partners Fireworks, Together, and Baseten. Zero Data Retention is also supported.
Show more
Claude Opus 5 is now available in Cursor!
It matches Fable 5 on CursorBench (66.7 vs 66.5 at default effort) at half the price. Unlike Fable, it's also compatible with Zero Data Retention.
Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand.
Router delivers frontier-quality results at 60% lower cost.
We had a team of agents rebuild SQLite from its 835-page manual.
It created a replica in Rust which passed 100% of a held-out test suite.
Interestingly, cost varied 15x depending on which model mix we used.
Show more
See how every model compares:
GPT-5.6 Sol, Terra, and Luna are now available in Cursor.
On CursorBench, Sol scores 67.2%.
We've partnered with SpaceXAI to train Grok 4.5.
It’s our most powerful model yet and the first we've built for more than software engineering.
Claude Fable 5 is available again in Cursor.
It leads all models on CursorBench, but is the most expensive per task.
Claude Sonnet 5 is now available in Cursor.
On CursorBench, it's a meaningful step up from Sonnet 4.6: 57% vs. 49%.
Introducing Cursor for iOS.
Build from anywhere by launching always-on cloud agents. Or remotely control agents running on your computer from the app.
Composer 2.5 is 75% off in the app now through July 5.
Show more
We're sharing new research on how models hack public benchmarks.
The latest models, including Opus 4.8 and Composer 2.5, learn to retrieve solutions from the internet or git history.
When we apply a stricter harness, eval scores drop significantly.
Show more
You can now delegate tasks to Cursor directly from Notion.
It's built on the Cursor SDK, so every cloud agent runs on the same models, harness, and runtime that power Cursor.
@Cursor on any spec or assign it a task to open a PR your whole team can review.
Show more
Plugins can now include prebuilt canvases.
Use the Atlassian canvas to see a real-time view of all your issues, projects, and documents.