Cursor (@cursor_ai) header
Cursor (@cursor_ai) profile picture

Coding agent for building ambitious software

Joined August 2023
Photo by Cursor (@cursor_ai)Photo by Cursor (@cursor_ai)Photo by Cursor (@cursor_ai)Photo by Cursor (@cursor_ai)Photo by Cursor (@cursor_ai)Photo by Cursor (@cursor_ai)Photo by Cursor (@cursor_ai)Photo by Cursor (@cursor_ai)Photo by Cursor (@cursor_ai)Photo by Cursor (@cursor_ai)
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.
2,474
4,558
1,821
54,950
9,885,226
Your agents can now coordinate with your teammates’ agents. Projects has been rebuilt for multiplayer: every teammate and their agents can now work together in one unified workspace.
406
247
337
4,009
558,907
Team Projects provides shared context for every teammate and their agents. Agents share plans before they start, flag conflicts while they work, and unblock each other’s tasks across the team. Launching in beta today cursor.com/blog/projects-mul…
12
9
5
201
32,763
Gemini 4 Carbon is now available in Cursor! At high effort, it's the top model on CursorBench at 60.4%
287
287
237
4,992
613,185
Gemini 4 Carbon is 50% off through November 30, at $2/M input and $10/M output tokens, rising to $4/M and $20/M on December 1. Compare every effort level: cursor.com/evals
2
11
3
206
40,032
Claude Fable 5.2 is now available in Cursor! At max effort, it's the top model on CursorBench at 60%. Fable 5.2 scores 56.9% on CursorBench at default effort, up from 49.2% for Fable 5.1.
226
142
78
2,843
178,395
Fable 5.2 is priced at $8/M input and $40/M output tokens, 20% less than Fable 5.1. Effort levels behave differently from Fable 5.1's, so start at the default rather than carrying over your old setting. Compare every effort level: cursor.com/evals
11
4
1
148
25,471
You can now build live apps in Cursor and share them with a link. Agents have made it easier to write code, but most apps never make it off localhost. Describe the tool you want - Cursor will build it, set up a database, run deterministic and agentic security checks, and deploy.
499
365
370
3,762
502,049
Teams across Cursor are already using it to build live dashboards, customer presentations, internal ops tools, onboarding programs, and developer portals. Available now on all paid plans. Update to the latest version of Cursor to build your first app: cursor.com/changelog
22
10
181
28,990
We identified a security incident affecting a modified Claude Code VS Code extension accessed through our Cursor IDE extension marketplace, impacting at most 5,000 users. This malicious version of the extension was not developed by Anthropic. It does not impact other extensions downloaded from the cursor.com/marketplace, Grok Bot, Grok or our other SpaceXSI products. In response, we took down our extension marketplace this afternoon, worked with relevant providers to neutralize the malware, and have reinstated the marketplace after confirming there is no further risk. If affected, please review instructions in this blog post to understand how to find the malicious package and establish a path to mitigate any potential impact. We are asking all customers update to Claude Code for VS Code version 2.1.314: cursor.com/blog/claude-code-…
567
1,080
727
7,046
1,309,571
New in Cursor design mode: Annotate. Give agents visual prompts: edit elements, draw on the page, and review your designs at different screen sizes.
367
245
255
4,180
372,788
DeepSeek V4.1 Flash is now available in Cursor! Every effort level sits on the CursorBench cost frontier: from $0.60 to $0.98 per task, no model scores higher. Turn it on in Cursor Settings > Models.
358
214
220
4,103
371,903
The Agent SDK is now available. Define agents as code, with prompts in Markdown and tools in TypeScript. Deploy them on our hosted infrastructure, or run them on your own. Built-in evals let you measure every change and make your agents better over time.
425
281
278
3,934
415,392
Cursor can now control your computer. Agents can drive desktop apps like the iOS Simulator to test the features they build.
538
469
446
6,424
424,440
Computer Use lets agents click and type across any app on your computer, not just the browser. Cursor uses it on its own when a task needs it. You can also ask for it by @-mentioning Computer Use in your prompt. Update Cursor to try it: cursor.com/download
32
12
24
301
34,778
Cloud agents can now build interactive canvases. Ask for a dashboard or report while the agent works, then share the finished canvas with your team as a link.
253
148
94
2,650
180,122
The Environments API is now available in beta. Create and manage cloud agent environments programmatically, including the repos they clone and the environment.json setup they run.
31
6
4
176
29,505
Muse Wonder from Meta Superintelligence Labs is now available in Cursor! It scores 46.1% on CursorBench at default effort, the highest of any Muse model. Priced at $4/M input and $20/M output tokens.
246
103
83
2,197
160,538
Gemini 4 Argon is now available in Cursor! It scores 52.8% on CursorBench at default effort, on par with Opus 5.5. Priced at $2/M input and $10/M output tokens.
272
208
135
4,457
311,037
Origin, Cursor’s code hosting platform, now supports over 20 integrations. Connect your repos to tools for CI, deployments, code review, security, monitoring, and project management.
154
137
89
2,116
195,009
The marketplace is now open to public submissions, so any team making developer tools can publish an app.
8
9
2
147
26,246
Cursor is now part of The X Subscription. Current Cursor subscribers can keep their plan or switch to The X Subscription. Paid plans share one usage pool across Cursor, Grok Build, and other Grok products, with twice the coding usage on Grok models as the equivalent Cursor plan. Premium, Super, and Ultra also include Grok Bot. To make room for more Grok usage, third-party models in Cursor move to API pricing on the new plans. We'll keep working to make your usage go further, with more compute, better inference, and more token-efficient models. The X Subscription is available at cursor.com/pricing.
We've unified plans across Grok, Cursor, and X Premium. Introducing The X Subscription.
607
451
374
6,467
789,199
The first chart usually raises the next question. Ask it in the same chat and /visualize answers with a new chart.
Cursor can now build charts and diagrams right in the chat. Use /visualize to analyze data and see the answer inline. Available now in the Agents Window.
120
76
19
1,283
84,956
Claude Haiku 5.5 is now available in Cursor! On shorter requests, it costs 10x less than Claude Haiku 4.5. Turn it on in Cursor Settings > Models.
179
126
95
2,749
265,772
Claude Haiku 5.5 is priced at $0.10/M input and $0.50/M output tokens, or $0.50/M and $2.50/M above 100k input tokens. Claude Sonnet 5.5 cache reads are also now $0.10/M tokens, down from $0.20/M. Compare Haiku 5.5 on CursorBench: cursor.com/evals
18
4
4
117
34,892
You can now control agents on your computer from your phone. Check in, reply, or start new tasks from the Cursor iOS app.
298
153
113
2,296
180,113
The agent runs on your computer, so it keeps working even if your phone loses signal.
5
5
1
125
25,837
You can now steer Cursor SDK agents while they run. run.steer() adds your message to the next turn. If a subagent is mid-task, it moves to the background and keeps working.
146
83
66
1,338
142,950
Background subagents now report back. Their results return to the parent as a follow-up turn on the same run, so stream() and wait() carry through until every subagent finishes.
9
2
1
97
15,823
When Rollouts catches a regression, it finds the offending PR and opens an issue. One click starts a cloud agent to fix it. Rollouts usage credits are included through Oct 3.
Introducing Rollouts. Rollouts write a monitoring plan, then watch changes as they deploy. Deployments are verified, so regressions are caught before users see them.
92
45
16
864
80,130