cursor

Cursor's voice chat (Grok Voice) and Antigravity 2.29's Voice Mode (Gemini Live) let developers talk with coding agents while they work; the sources differ on surfaces and limits.

Cursor says modified Claude Code extension versions 2.1.312 and 2.1.313 were available in its VS Code extension marketplace on October 29 and tried to install an SSH backdoor; it says Anthropic did not develop them and reports it removed them and rotated keys.

Between August and October 2026, Cursor, GitHub and Anthropic described repository infrastructure designed around agent load; they differ on whether to keep Git, and the performance figures are self-reported.

Cursor says its Origin git forge now integrates with over 20 apps, and any team building developer tools can submit one; Origin remains in early beta.

Cursor's iOS app can now list and message agents running on a paired computer. The agents stay local, so the machine must remain on and online.

Cursor released two automated bots that watch code from pull request to production and scan every PR for security flaws, six weeks after acquiring startup Firetiger.

A Concordia University benchmark found Cursor, Claude Code, and Codex Desktop let malicious GitHub issues bypass their safety guardrails in up to 79.2% of attempts, with GPT-based agents far more vulnerable than Claude Code.

Cursor's principal systems engineer Vicent Martí describes Continuity, a write-ahead-log architecture on S3 that replaces three-phase-commit consensus and powers the Origin hosting platform.

Scott Wu says Cognition is "not for sale" after Bloomberg reported SpaceX approached the Devin maker days after closing its $60 billion Cursor deal.

Cursor's new GitHub-rival hosting platform went into beta the same day a six-hour GitHub outage knocked out the feature it depends on.

SpaceX completed its all-stock acquisition of AI coding tool Cursor on August 14, giving the startup access to SpaceX's GPU fleet.

SpaceXAI's Grok 4.5, trained alongside Cursor, is priced at $2 per million input tokens and $6 per million output tokens; Musk calls it 'an Opus-class model, but faster, more token-efficient and lower cost.'