Cursor
2 Tools · 33 Intel
Cursor is the trade name of Anysphere, Inc., the San Francisco company behind the Cursor AI coding agent and development environment. Michael Truell, Sualeh Asif, Arvid Lunnemark and Aman Sanger incorporated the company in 2022 while students at MIT. SpaceX completed its acquisition of Anysphere on August 14, 2026, and Cursor now operates as a wholly owned SpaceX subsidiary.
Tools
AI-powered code editor built on VS Code, combining inline AI assistance, chat, and an agent mode.
Repository holding Cursor's plugin specification along with its first-party plugins.
Intel
Cursor traces twenty years of Git hosting design and explains why it operates its own storage layer, Origin, as a database rather than a filesystem, with the scaling limits that pushed it there.
Cursor added Claude Haiku 5.5, priced at $0.10/M input and $0.50/M output (rising to $0.50/$2.50 above 100k input), and halved Sonnet 5.5 cache read pricing to $0.10/M. Enable it in Settings under Models.
Cursor adds Gemini 4 Argon, reporting 52.8% on CursorBench at default effort, comparable to Opus 5.5. Pricing is $2 per million input tokens and $10 per million output tokens.
Cursor added Anthropic's Sonnet 5.5 as a selectable model, saying it matches Opus on many tasks. Coding-agent users get a new option for the model tier used in day-to-day editing and agent runs.
Cursor now lets cloud agents execute on infrastructure you control, including autoscaling machine pools, while the agent loop remains in Cursor. Supported sandbox providers include AWS Lambda, Coder, Cloudflare, Daytona, E2B, Modal, Namespace, and Vercel.
Cursor set two generations of multi-agent swarm against the same task, writing SQLite from scratch, and found the newer coordination scheme matched output quality at a fraction of the compute. The argument: orchestration efficiency now drives agent economics.
Cursor has added Meta's Muse Spark 1.3 to its model lineup, with full benchmark results published on Cursor's own CursorBench.
Cursor is now sold through The X Subscription, with one usage pool shared across Cursor and Grok products and 2x coding usage on Grok models. On the new plans third-party models are billed at API list price. Current Cursor subscribers can keep their plan.
Claude Opus 5.5 is now available in Cursor and tops CursorBench at 57.8% (Max) while costing 40% less per task than Opus 5, per Cursor's own benchmark data.