Cursor can now work autonomously over longer horizons to complete larger, more complex tasks. Long-running agents plan first and finish more difficult work without human intervention.
In research preview and internal testing, long-running agents completed work that was previously too hard for regular agents. This led to larger, more complete PRs with fewer obvious follow-ups.
Cursor's long-running agent is now available at cursor.com/agents for Ultra, Teams, and Enterprise plans.
Agents are solving increasingly complex, long-running tasks across your codebase. This release introduces new agent harness improvements for better context management, as well as many quality-of-life fixes in the editor and CLI.
Subagents are independent agents specialized to handle discrete parts of a parent agent's task. They run in parallel, use their own context, and can be configured with custom prompts, tool access, and models.
The result is faster overall execution, more focused context in your main conversation, and specialized expertise for each subtask.
Cursor includes default subagents for researching your codebase, running terminal commands, and executing parallel work streams. These will automatically start improving the quality of your agent conversations in the editor and the Cursor CLI.
Optionally, you can define custom subagents. Learn more in our docs.
Cursor now supports Agent Skills in the editor and CLI. Agents can discover and apply skills when domain-specific knowledge and workflows are relevant. You can also invoke a skill using the slash command menu.
Define skills in SKILL.md files, which can include custom commands, scripts, and instructions for specializing the agent’s capabilities based on the task at hand.
Compared to always-on, declarative rules, skills are better for dynamic context discovery and procedural “how-to” instructions. This gives agents more flexibility while keeping context focused.
Generate images directly from Cursor's agent. Describe the image in text or upload a reference to guide the underlying image generation model (Google Nano Banana Pro).
Images are returned as an inline preview and saved to your project's assets/ folder by default. This is useful for creating UI mockups, product assets, and visualizing architecture diagrams.
On the Enterprise plan, Cursor Blame extends traditional git blame with AI attribution, so you can see exactly what was AI-generated versus human-written.
When reviewing or revisiting code, each line links to a summary of the conversation that produced it, giving you the context and reasoning behind the change.
Cursor Blame distinguishes between code from Tab completions, agent runs (broken down by model), and human edits. It also lets you track AI usage patterns across your team's codebase.
The interactive Q&A tool used by agents in Plan and Debug mode now lets agents ask clarifying questions in any conversation.
While waiting for your response, the agent can continue reading files, making edits, or running commands, then incorporate your answer as soon as it arrives.
You can also build custom subagents and skills that use this tool by instructing them to "use the ask question tool."
Use agent to start working with the upgraded Cursor CLI in your terminal.
MCP server definitions and tools now live as JSON files in .cursor. Agents discover and load MCPs only when needed, reducing token usage and keeping the context focused.
Agents can now proactively request switching modes mid-conversation when it detects a different mode would be more effective for the task. You can also auto-approve and auto-reject specific transitions.
Fast read-only diff viewer improved performance of the review changes pane.
It's now faster to open and resize any chats which used inline code blocks.
Agents can now read PDFs, which you can attach in chats as context.
CLI can be linked to run as a service account.
Improved capabilities & coverage for hooks: stop hook; modify prompts beforeSubmitPrompt ; PreToolUse and PostToolUse hooks.
Hook commands now start 40x faster.
The in-editor browser is now 10× faster at navigation, with more reliable click actions, drag-and-drop support, and improved text input handling. Agents can also lock the browser while working to prevent accidental interference.
Light mode is now supported in the Cursor web dashboard.
We've removed the peek sidebar based on your feedback.
Windows notifications now have accept/reject buttons like MacOS.
Users who choose to "Run Everything" will never have their agents blocked.
Editing skills and rules files no longer requires approval in sandboxes.
Git writes are now allowed in sandboxes.
File edit approvals persist for the entire agent session in sandboxes.
Out-of-workspace folder edits can be allowed for the session in sandboxes.
Added team and MDM hooks support to CLI with more efficient execution.
Added more hooks to CLI already supported in the editor. See the full list of hooks in our docs.
Added compatibility with Claude Code hooks in CLI.
Faster startup on warm starts in CLI.
Unified CLI permissions with the editor, including Run Everything, Auto-Run in Sandbox (if available), and Ask Every Time (allowlist).
Push your local conversation to a Cloud Agent and let it keep running while you're away. Prepend & to any message to send it to the cloud, then pick it back up on web or mobile at cursor.com/agents.
Connect Cursor to external tools and data sources with a new login flow supporting automatic callback handling. The agent gets access to authenticated MCPs immediately.
Use /mcp list for an updated interactive MCP menu to browse, enable, and configure MCP servers at a glance.
Added hooks for session start/end, prompt, and stop for customizing agent lifecycle events.
See Cursor streaks and stats with /usage.
Added WebFetch, WebSearch tools, & approval options for granular controls over web search and fetch requests from MCP tools.
Added /about for seeing basic details about your environment and Cursor CLI setup.
Faster message queueing and UX.
Shift+Enter for newlines now works in iTerm2, Ghostty, Kitty, Warp, and Zed. Run /setup-terminal to auto-configure /Option+Enter Apple Terminal, Alacritty, or VS Code. Ctrl+J and \+Enter work universally as alternatives.
Smarter terminal environment detection for optimal keybindings and display.
Better markdown rendering with proper links, tables, and rules.
Menu resize handling, long line truncation, and stable state on window changes.
/list removed. Use /resume to see all prior conversations.
/models removed. Use /model to see all models or select a model.
Fixed process hangs and silent failures. Agent runs should be more stable with fewer errors.
For this holiday release, we've focused entirely on fixing bugs and improving stability.
This includes the core agent, layout controls, viewing code diffs, and more. We will be slowly rolling these updates out over the week, ensuring there are no regressions during your holiday coding.
Cursor now separates processes running for user-installed extensions and built-in Cursor extensions, such as codebase indexing.
Improved stability around how the agent respects auto-run preferences to prevent asking for approval on all changes if the user has selected run all or sandbox.
Improved integrated browser to support opening multiple tabs.
Fixed chat loading, where sometimes restarts or updates could cause past chats to be inaccessible.
Update button will show less frequently, and cool down for significantly longer when dismissed.
Fixed issue where generating plans in Plan Mode would steal focus from other active panes.
Fixed integrated browser menubar issue on Windows.
Improved parallel agent stability and quality when using worktrees.
Improved stability for rolling back to previous checkpoints in agent conversations.
Improved ability to edit and drag queued message to agent.
Fixed an edit bug caused old_str replace failed error message.
Fixed rare prompt input and @-menu delay when opening.
Fixed a bug where voice message start icon would not display.
Fixed files deleted in a worktree not being removed when applying changes.
Fixed accept/reject controls not appearing for file edits in parallel agents.
Fixed incorrect model names displaying in parallel agents after applying.
Fixed resubmitting the first model in a parallel agent run after applying.
Fixed multiple models toggle bug with non-git-root directories.
Fixed model mismatch in Plan Mode when using worktrees.
Fixed worktrees requiring edit approval outside of otherwise defined auto-run settings.
Fixed a rare bug where a user could be logged out on submission from abuse checks.
Fixed unread states persisting in the agent sidebar after Plan Mode Q&A.
Fixed issue where selected panes were being reset on version upgrades.
Fixed ⌘+N to only create new agent conversations when focused in chat view.
Fixed issue with native tabs not displaying correct with agent layout.
Fixed issue with displaying terminals on the right side layout.
Fixed issue where the bottom of the screen content could be cut off in some scenarios.
Added new keybindings (⌘+⌥+⇥) for switching between user-defined layouts.
View a file explorer when clicking on the repo name in the top navigation bar.
File explorer now defaults open during onboarding.
Moved the new agent icon from the main title bar into the panel itself based on feedback.
Added a "More Actions" ellipsis to hide the chat and configuring positioning directly.
Added keyboard shortcuts into display for the "More Actions" menu.
Selecting filenames directly from change summary focuses that file in the review pane.
Fixed bug where keep/undo all buttons would not show up in the UI.
Fixed bug where keep/undo all would flip sides when scrolling from files list to composer toolbar.
Improved visibility of changing between split/unified diffs for reviewing changes.
Added support for Static Client headers in MCP OAuth w/ scopes and state.
MCP OAuth servers now open new auth tabs for previously authenticated servers on startup.
It's now easier to customize your default layout across workspaces.
We've included four default layouts: agent, editor, zen, and browser. You can use Command (⌘) + Option (⌥) + Tab (⇥) to switch between layouts, or easily jump between different workspaces. Additionally, you can move backwards in this list by including Shift (⇧), similar to macOS.
Cursor can now work autonomously over longer horizons to complete larger, more complex tasks. Long-running agents plan first and finish more difficult work without human intervention.
In research preview and internal testing, long-running agents completed work that was previously too hard for regular agents. This led to larger, more complete PRs with fewer obvious follow-ups.
Cursor's long-running agent is now available at cursor.com/agents for Ultra, Teams, and Enterprise plans.
Agents are solving increasingly complex, long-running tasks across your codebase. This release introduces new agent harness improvements for better context management, as well as many quality-of-life fixes in the editor and CLI.
Subagents are independent agents specialized to handle discrete parts of a parent agent's task. They run in parallel, use their own context, and can be configured with custom prompts, tool access, and models.
The result is faster overall execution, more focused context in your main conversation, and specialized expertise for each subtask.
Cursor includes default subagents for researching your codebase, running terminal commands, and executing parallel work streams. These will automatically start improving the quality of your agent conversations in the editor and the Cursor CLI.
Optionally, you can define custom subagents. Learn more in our docs.
Cursor now supports Agent Skills in the editor and CLI. Agents can discover and apply skills when domain-specific knowledge and workflows are relevant. You can also invoke a skill using the slash command menu.
Define skills in SKILL.md files, which can include custom commands, scripts, and instructions for specializing the agent’s capabilities based on the task at hand.
Compared to always-on, declarative rules, skills are better for dynamic context discovery and procedural “how-to” instructions. This gives agents more flexibility while keeping context focused.
Generate images directly from Cursor's agent. Describe the image in text or upload a reference to guide the underlying image generation model (Google Nano Banana Pro).
Images are returned as an inline preview and saved to your project's assets/ folder by default. This is useful for creating UI mockups, product assets, and visualizing architecture diagrams.
On the Enterprise plan, Cursor Blame extends traditional git blame with AI attribution, so you can see exactly what was AI-generated versus human-written.
When reviewing or revisiting code, each line links to a summary of the conversation that produced it, giving you the context and reasoning behind the change.
Cursor Blame distinguishes between code from Tab completions, agent runs (broken down by model), and human edits. It also lets you track AI usage patterns across your team's codebase.
The interactive Q&A tool used by agents in Plan and Debug mode now lets agents ask clarifying questions in any conversation.
While waiting for your response, the agent can continue reading files, making edits, or running commands, then incorporate your answer as soon as it arrives.
You can also build custom subagents and skills that use this tool by instructing them to "use the ask question tool."
Use agent to start working with the upgraded Cursor CLI in your terminal.
MCP server definitions and tools now live as JSON files in .cursor. Agents discover and load MCPs only when needed, reducing token usage and keeping the context focused.
Agents can now proactively request switching modes mid-conversation when it detects a different mode would be more effective for the task. You can also auto-approve and auto-reject specific transitions.
Fast read-only diff viewer improved performance of the review changes pane.
It's now faster to open and resize any chats which used inline code blocks.
Agents can now read PDFs, which you can attach in chats as context.
CLI can be linked to run as a service account.
Improved capabilities & coverage for hooks: stop hook; modify prompts beforeSubmitPrompt ; PreToolUse and PostToolUse hooks.
Hook commands now start 40x faster.
The in-editor browser is now 10× faster at navigation, with more reliable click actions, drag-and-drop support, and improved text input handling. Agents can also lock the browser while working to prevent accidental interference.
Light mode is now supported in the Cursor web dashboard.
We've removed the peek sidebar based on your feedback.
Windows notifications now have accept/reject buttons like MacOS.
Users who choose to "Run Everything" will never have their agents blocked.
Editing skills and rules files no longer requires approval in sandboxes.
Git writes are now allowed in sandboxes.
File edit approvals persist for the entire agent session in sandboxes.
Out-of-workspace folder edits can be allowed for the session in sandboxes.
Added team and MDM hooks support to CLI with more efficient execution.
Added more hooks to CLI already supported in the editor. See the full list of hooks in our docs.
Added compatibility with Claude Code hooks in CLI.
Faster startup on warm starts in CLI.
Unified CLI permissions with the editor, including Run Everything, Auto-Run in Sandbox (if available), and Ask Every Time (allowlist).
Push your local conversation to a Cloud Agent and let it keep running while you're away. Prepend & to any message to send it to the cloud, then pick it back up on web or mobile at cursor.com/agents.
Connect Cursor to external tools and data sources with a new login flow supporting automatic callback handling. The agent gets access to authenticated MCPs immediately.
Use /mcp list for an updated interactive MCP menu to browse, enable, and configure MCP servers at a glance.
Added hooks for session start/end, prompt, and stop for customizing agent lifecycle events.
See Cursor streaks and stats with /usage.
Added WebFetch, WebSearch tools, & approval options for granular controls over web search and fetch requests from MCP tools.
Added /about for seeing basic details about your environment and Cursor CLI setup.
Faster message queueing and UX.
Shift+Enter for newlines now works in iTerm2, Ghostty, Kitty, Warp, and Zed. Run /setup-terminal to auto-configure /Option+Enter Apple Terminal, Alacritty, or VS Code. Ctrl+J and \+Enter work universally as alternatives.
Smarter terminal environment detection for optimal keybindings and display.
Better markdown rendering with proper links, tables, and rules.
Menu resize handling, long line truncation, and stable state on window changes.
/list removed. Use /resume to see all prior conversations.
/models removed. Use /model to see all models or select a model.
Fixed process hangs and silent failures. Agent runs should be more stable with fewer errors.
For this holiday release, we've focused entirely on fixing bugs and improving stability.
This includes the core agent, layout controls, viewing code diffs, and more. We will be slowly rolling these updates out over the week, ensuring there are no regressions during your holiday coding.
Cursor now separates processes running for user-installed extensions and built-in Cursor extensions, such as codebase indexing.
Improved stability around how the agent respects auto-run preferences to prevent asking for approval on all changes if the user has selected run all or sandbox.
Improved integrated browser to support opening multiple tabs.
Fixed chat loading, where sometimes restarts or updates could cause past chats to be inaccessible.
Update button will show less frequently, and cool down for significantly longer when dismissed.
Fixed issue where generating plans in Plan Mode would steal focus from other active panes.
Fixed integrated browser menubar issue on Windows.
Improved parallel agent stability and quality when using worktrees.
Improved stability for rolling back to previous checkpoints in agent conversations.
Improved ability to edit and drag queued message to agent.
Fixed an edit bug caused old_str replace failed error message.
Fixed rare prompt input and @-menu delay when opening.
Fixed a bug where voice message start icon would not display.
Fixed files deleted in a worktree not being removed when applying changes.
Fixed accept/reject controls not appearing for file edits in parallel agents.
Fixed incorrect model names displaying in parallel agents after applying.
Fixed resubmitting the first model in a parallel agent run after applying.
Fixed multiple models toggle bug with non-git-root directories.
Fixed model mismatch in Plan Mode when using worktrees.
Fixed worktrees requiring edit approval outside of otherwise defined auto-run settings.
Fixed a rare bug where a user could be logged out on submission from abuse checks.
Fixed unread states persisting in the agent sidebar after Plan Mode Q&A.
Fixed issue where selected panes were being reset on version upgrades.
Fixed ⌘+N to only create new agent conversations when focused in chat view.
Fixed issue with native tabs not displaying correct with agent layout.
Fixed issue with displaying terminals on the right side layout.
Fixed issue where the bottom of the screen content could be cut off in some scenarios.
Added new keybindings (⌘+⌥+⇥) for switching between user-defined layouts.
View a file explorer when clicking on the repo name in the top navigation bar.
File explorer now defaults open during onboarding.
Moved the new agent icon from the main title bar into the panel itself based on feedback.
Added a "More Actions" ellipsis to hide the chat and configuring positioning directly.
Added keyboard shortcuts into display for the "More Actions" menu.
Selecting filenames directly from change summary focuses that file in the review pane.
Fixed bug where keep/undo all buttons would not show up in the UI.
Fixed bug where keep/undo all would flip sides when scrolling from files list to composer toolbar.
Improved visibility of changing between split/unified diffs for reviewing changes.
Added support for Static Client headers in MCP OAuth w/ scopes and state.
MCP OAuth servers now open new auth tabs for previously authenticated servers on startup.
It's now easier to customize your default layout across workspaces.
We've included four default layouts: agent, editor, zen, and browser. You can use Command (⌘) + Option (⌥) + Tab (⇥) to switch between layouts, or easily jump between different workspaces. Additionally, you can move backwards in this list by including Shift (⇧), similar to macOS.
