VS Code fork with inline AI, agent mode for multi-file changes, and a built-in Bugbot reviewer. The default if you want the AI inside the editor instead of in a terminal or chat tab.
Projects enables managing feature development, migrations, and full apps with a coordinator agent that plans work, delegates to subagents, and maintains context over months. The coordinator runs agents in parallel and can watch Slack channels or run on schedules to automatically pick up work without explicit prompting.
Projects maintain context over months of work, with a coordinator agent that plans work and delegates to subagents running in parallel. Projects can watch Slack channels or run on schedules to take action without being prompted, keeping shared context across all agents involved.
Projects is a new feature that maintains context over months of work and delegates tasks to thousands of subagents. A coordinator agent plans the work and delegates to implementation agents that run in parallel. Projects can watch Slack channels, follow PRs, or run on a schedule to take action automatically without prompting.
Cloud agents can now execute on internal infrastructure, keeping codebases and secrets on-premise. Features include dynamic pool scaling that grows with demand and hibernates idle workers, plus computer use (clicks, typing, screenshots) on Linux and Mac self-hosted workers.
Cursor now supports self-hosted machines that keep tool execution entirely in your infrastructure. Features include dynamic pool scheduling for teams with auto-scaling capacity, execution on existing platforms (AWS Lambda, Coder, Cloudflare, Modal, etc.), and computer use support on Linux and Mac for browser automation and desktop interaction.
Cursor now supports running cloud agents on self-hosted infrastructure including AWS Lambda, Coder, Cloudflare, and others, keeping your code and secrets on internal machines. The platform includes dynamic pool scheduling for teams and computer use on Linux and Mac through self-hosted workers.
Self-hosted machines keep tool execution in your own network with infrastructure like AWS Lambda, Cloudflare, and Modal. Dynamic pool scheduling lets team pools scale capacity with demand and hibernate idle machines. Agents can now use computer use (clicking, typing, screenshots) on Linux and Mac.
Cursor now supports self-hosted machines that keep tool execution entirely within your own network infrastructure. Features include dynamic pool scheduling for team workloads that scale with demand, support for various sandbox platforms (AWS Lambda, Coder, Cloudflare, etc.), and computer use on Linux and Mac for local desktop automation.
Cloud agents can now run on your own infrastructure including AWS Lambda, Vercel, and other platforms, keeping code and secrets on internal machines. Dynamic pool scheduling scales capacity automatically based on demand and supports computer use on Linux and Mac.
Self-hosted workers can run cloud agent tool calls locally, keeping your codebase and secrets on internal machines. Features include dynamic pool scheduling for teams, support for AWS Lambda and other infrastructure providers, and computer use on Linux and Mac.