Cloud Agents Efficiency Update

Cursor's cloud agents now burn 20-30% fewer tokens per run and up to 80% fewer on computer-use runs, which directly changes how long a delegated task can run inside a fixed budget.

• MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
• token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.

• postGLM 5.3 and GLM 5.3 Flash are now available in Cursor!
• postCursor adds /visualize for inline charts and diagrams
• postSonnet 5.5 lands in Cursor, positioned near Opus-level
• postClaude Opus 5.5 Tops CursorBench, Costs 40% Less

• postCloud agents now start 3x faster so you can hand them ambitious, long-running…Cursor
• postCursor cloud agents hold a goal, watch PRs, and run subagents on their own VMsCursor
• postCursor cloud agents can now execute on your own machines and sandbox providersCursor

Checking sign-in…

Loading comments…