@cursor_ai
Coding agent for building ambitious software
Claude Opus 5.5 is now available in Cursor! It's the new top model on CursorBench at 57.8% (Max) and costs 40% less per task than Opus 5.
Introducing Projects, a new way of working in Cursor. Rather than creating a chat for every task, you work with a coordinator agent in a single, persistent thread. Like @bot, your agent is always on, proactively manages work with subagents, and improves over time.
Projects can set reminders, run scheduled tasks, follow PRs to fix CI issues, watch Slack for bug reports, and more.
Muse Spark 1.3 from Meta is now available in Cursor!
Full results: cursor.com/cursorbench
You can now run Cursor cloud agents on your infrastructure, including pools of machines that automatically scale with demand. This lets you give agents access to internal services or specialized hardware, while the agent loop stays in Cursor.
Run agents on machines you manage or through supported sandbox providers like AWS Lambda, Coder, Cloudflare, Daytona, E2B, Modal, Namespace, and Vercel. cursor.com/blog/self-host…
Gemini 3.8 Flash is now available in Cursor!
Full results: cursor.com/cursorbench
Claude Fable 5.1 is now available in Cursor! It's the most capable model we’ve run on CursorBench 3.2, scoring 73.4% at max effort. We found it especially skilled at verifying its own work, allowing it to take on difficult coding tasks from start to finish.
You can now create new web apps with Cursor, store the code with Origin, and deploy to Vercel.
Learn more: cursor.com/changelog/star…
We're continuing to improve cloud agents in Cursor. They pick up work from events, hold a goal until it's met, and stay on course through long sessions.
Cursor can now monitor your PRs, watch a Slack thread, or run scheduled tasks. Cloud agents automatically subscribe to PRs they create and drive them to completion.
We're making Git hosting more reliable, performant, and scalable. This post traces 20 years of Git infrastructure and explains how that history led us to design and operate our Git storage, Origin, as if it were a database. cursor.com/blog/git-at-an…
Origin, our code hosting platform, is now live. It's fast, easy to use, and deeply integrated with Cursor. Get started by syncing your repos from GitHub.
We've partnered with some of the top GitHub integrations. Vercel, Buildkite, and Depot are already available with more coming soon.
Cursor is now part of @SpaceX. Today, we have officially closed our acquisition. We will join the @SpaceXAI team to help make Grok the world's most useful AI and improve Grok Build, Grok Bot, Grok API, Cursor, and more. SpaceX has built some of the most inspiring and impressive technology in the world, and we’re grateful for the opportunity to become part of such a special company. Onwards.
We’re excited to welcome the Firetiger team to Cursor! Together, we're building agents that can follow their work into production and fix what goes wrong. cursor.com/blog/firetiger
Cloud agents now start 3x faster so you can hand them ambitious, long-running tasks to execute from start to finish. This performance improvement comes from builds: ready-to-use development environments that Cursor prepares continuously in the background, at no additional cost.
Builds also make agents more resilient and easier to debug. When a new build fails, it never goes live. Agents keep working from the last successful build while you debug in the background.
Cursor now supports Agent Plugins, an open standard for bundling skills and MCP servers for use across agents. x.com/vercel/status/…
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.
No model dominates every kind of task. Grok 4.5 offers strong value on routine tasks. GPT-5.6 Sol is effective on planning and codebase comprehension. Opus 5 excels for execution-heavy work, and Fable 5 on debugging and visual implementation.
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.
MoK now powers training across tens of thousands of GPUs at Cursor. In production, it raised end-to-end training throughput by 1.41x over our previous DeepEP-based stack.
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.
Install them from the Customize page in Cursor. Learn more: cursor.com/changelog/goog…
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. x.com/cursor_ai/stat…
In December, 1 in 10 of our merged PRs came from cloud agents. Today, it’s 56%, as we use cloud agents to complete longer engineering tasks from start to finish. We got here by giving agents their own cloud computers and letting them fix and improve their environments.
Read more about how we set up our cloud agent environment: cursor.com/blog/cloud-age…
Cursor is now on iPad. All the power of Cursor on iPhone, with more room to work with agents.
New to both iPhone and iPad: an inbox to stay organized, and a review experience that covers the full PR, including comments, checks and approvals.
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.
Cursor Start also includes: - Autonomous cloud agents that ship work while you're away - Cursor for iOS to steer them from your phone - Plugins, MCP servers, hooks, and skills to extend your workflow Learn more: cursor.com/blog/cursor-st…
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.
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.
See how all of the models compare here: cursor.com/evals
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.
Select Auto mode and whether you’d like to optimize for Intelligence, Balance, or Cost. Cursor Router analyzes each request and routes to the best model for the job: frontier models when the work demands them and price-efficient models when it doesn't.
We've doubled usage limits for all individual and teams plans! These limits apply to Grok, Composer, and any new Cursor models.
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.
Introducing side chats, a new way to ask questions and explore ideas without interrupting your main conversation. Each side chat is a durable agent conversation you can @-mention to bring context back into the main thread.
You can now search agent transcripts to find past agent chats. Cursor builds a local search index that delivers fast search across thousands of conversations.
GPT-5.6 Sol, Terra, and Luna are now available in Cursor. On CursorBench, Sol scores 67.2%.
See how every model compares: cursor.com/evals
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.
Try it out in Cursor with double usage for the first week. cursor.com/blog/grok-4-5
Claude Fable 5 is available again in Cursor. It leads all models on CursorBench, but is the most expensive per task.
See how Claude Fable 5 compares across every model: cursor.com/evals
Claude Sonnet 5 is now available in Cursor. On CursorBench, it's a meaningful step up from Sonnet 4.6: 57% vs. 49%.
See our full model rankings: cursor.com/evals
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.
Stay in the loop with Live Activities, and get notified when an agent finishes or needs your input. Review demos and diffs before merging PRs from your phone. cursor.com/blog/ios-mobil…
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.
More on how we're constraining eval environments so that scores better reflect model intelligence: cursor.com/blog/reward-ha…
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.
More on how Notion built it with the Cursor SDK: cursor.com/blog/notion
Cursor now shows you a leaderboard of the most popular plugins, skills, and MCPs across your team. Add any to your setup with one click from the new Customize page.
Plugins can now include prebuilt canvases. Use the Atlassian canvas to see a real-time view of all your issues, projects, and documents.
Three announcements from our keynote at Compile, including how we're training a new model with SpaceX.
Introducing /automate, a skill for agents to set up automations for you. Describe your task in plain language. Cursor configures the triggers, instructions, and tools.
Cursor Automations now support an emoji trigger in Slack. React to any message to kick off a run.
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.
Cursor can now help you set up your dev environment in the cloud in under 10 minutes. Your environment is captured in a reusable snapshot, so future cloud agents start up faster with the ability to test changes and iterate until outputs are verified.
Learn more: cursor.com/changelog/clou…
It's now faster and easier to set up cloud environments. Environments are saved as snapshots so future agents start up faster and can test changes until the output is verified.
We're launching code storage and git hosting. Origin gives teams and agents a place to host, review, and collaborate on code. Available this fall. Join the waitlist. cursor.com/origin-waitlist
We're excited to join forces with @SpaceX to advance the frontier of useful AI. Expect significant improvements to Cursor soon. x.com/SpaceX/status/…
Auto-review is now the default for all new users. A classifier subagent reviews actions in context before deciding whether to allow, block, or ask for approval. Our evals show it's 97% accurate, with most misses near ambiguous edges.
More on how we built it: cursor.com/blog/agent-aut…
Cursor’s code review agent is now over 3x faster, 22% cheaper, and finds 10% more bugs. You can also use /review to run Bugbot locally to catch and fix issues before pushing code.
Learn more: cursor.com/blog/bugbot-up…
See how Claude Fable 5 compares across every model: cursor.com/evals
