2.3  · Changelog

Layout Customization and Stability Improvements

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.

Stability improvements

  • 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.

Layout customization

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.

 · Changelog

Enterprise Insights, Billing Groups, Service Accounts, and Improved Security Controls

Many of the largest software companies in the world have adopted Cursor for Enterprise. Here are some of the new features we're releasing today:

Conversation insights

Cursor can now analyze the code and context in each agent session to understand the type of work that is being done, including:

  • Category: Bug fixes, refactoring, explanation
  • Work Type: Maintenance, bug fixing, new features
  • Complexity: Difficulty and specificity of prompts

Enterprise customers can also extend these categories across their organization and teams. We protect your privacy by ensuring no PII or sensitive data is collected as part of these insights.

Shared agent transcripts

You can now share agent conversations with your team.

Generate a read-only transcript of any agent conversation to include in your PRs or internal documentation. Transcripts can be forked so others can start new agent conversations from the same context.

Billing groups

Cursor now supports billing groups for fine-grained visibility into where usage occurs.

Map usage and spend to the structure of your organization. Track spend by group, set budget alerts, and keep an eye on outliers. Understand which teams have the highest adoption of Cursor.

Linux sandboxing for agents

Sandboxing for agents supports Linux in addition to macOS.

This allows agents to work effectively within appropriate boundaries. Access is scoped to your workspace and can be configured to block unauthorized network and filesystem access.

Learn more about LLM safety and controls.

Service accounts

Service accounts are non-human accounts (and their API keys) that can configure Cursor, call APIs, and invoke cloud agents.

With service accounts, teams can securely automate Cursor-powered workflows without tying integrations to individual developers' accounts. This makes it easier to manage access, rotate credentials, and keep automations running even as people and roles change.

Service accounts will roll out to Enterprise accounts starting the week of 12/22.

Learn more about Cursor for Enterprise and talk to our team to learn more.

2.2  · Changelog

Debug Mode, Plan Mode Improvements, Multi-Agent Judging, and Pinned Chats

Debug Mode

Debug Mode helps you reproduce and fix the most tricky bugs.

Cursor instruments your app with runtime logs to find the root cause. It works across stacks, languages, and models.

Read more in our announcement.

Browser layout and style editor

Design and code simultaneously with a brand new browser sidebar and component tree.

Move elements, update colors, test layouts, and experiment with CSS in real time, then instantly apply changes to your codebase using agent. You can also click on multiple elements and describe changes in text to kick off an agent to make visual changes.

Plan Mode improvements

Plan Mode now supports inline Mermaid diagrams, allowing the agent to automatically generate and stream visuals into your plans. You also have more control over how you build them, with the option to send selected to-dos to new agents.

Multi-agent judging

When running multiple agents in parallel, Cursor will now automatically evaluate all runs and give a recommendation for the best solution.

The selected agent will have a comment explaining why it was picked. Judging of the best solution only happens after all parallel agents have finished.

Pinned chats

In the agent sidebar, pin chats at the top for future reference.

  • Browser protection can now be controlled through settings on cursor.com/dashboard.
  • Ask Mode can use a read-only terminal to get better answers, like checking git commits.
  • Multiple bug fixes and stability improvements for local parallel agents.
  • Plans now saved as files on disk by default.
  • Agent plans are now files that can be edited with normal tools.
  • System notification actions for terminal and MCP approval/rejection.
  • Fixed Cmd+Opt+Arrow chat switching and added Ctrl+Tab behavior.
  • Improved response performance for all AWS Bedrock users.
  • After focusing on the explorer pane, typing will automatically search.
  • Rules now support prompts, scripts, and more together inside folders.

2.1  · Changelog

Improved Plan Mode, AI Code Review in Editor, and Instant Grep

Improved Plan Mode

When creating plans, Cursor responds with clarifying questions to improve the plan quality. Cursor now shows an interactive UI to easily answer questions.

You can also ⌘+F to search inside generated plans.

AI Code Reviews

You can now find and fix bugs directly in Cursor with AI code reviews. It will look at your changes and find issues which you can see in the sidepanel.

This is in addition to Bugbot, which runs on your source control provider like GitHub (including Enterprise Server), GitLab, and more.

Instant Grep (Beta)

All grep commands run by the agent are now instant.

Instant grep is supported by all models in Cursor. It is also used when manually searching the codebase from the sidebar, including regexes and matching on word boundaries.

This improvement is slowly rolling out to 2.1 users over the next week.

  • Terminals have improved awareness of already running processes.
  • Project level hooks are now supported.
  • Minimum allowed version is now 1.5, minimum supported version is now 1.7.
  • New commit & push button added inside the agent diff review pane.
  • Custom modes have been removed, with the ability to export as custom commands.
  • Clicking files in review list jumps to diff in review pane.
  • Auto-accepting diff on commit now works at per-file level
  • Editor Title menu entries have been compressed into the show more menu.
  • VS Code Extension API upgraded to v1.105.1.
  • Rules in home folder (~/.cursor/rules) will be included in context
  • Use Cmd+K in dashboard to navigate between settings

  • Set origin allowlist from dashboard to restrict browser tools. Browser tools and navigation will then be blocked outside allowlist.
  • Define extension allowlist and blocklist for admins in dashboard
  • Renamed the Enterprise group policy name to Cursor.

We've shipped Cloud Agent support for

  • GitLab
  • GitHub Enterprise
  • Sentry
  • Plain

2.0  · Changelog

New Coding Model and Agent Interface

Multi-Agents

Manage agents in our new editor, with a sidebar for your agents and plans.

Run up to eight agents in parallel on a single prompt. This uses git worktrees or remote machines to prevent file conflicts. Each agent operates in its own isolated copy of your codebase.

Composer

Introducing our first agentic coding model. Composer is a frontier model that is 4x faster than similarly intelligent models.

Browser (GA)

Launched in beta in 1.7, browser for Agent is now GA. We've added additional support for Enterprise teams to use Browser in 2.0.

Browser can now be embedded in-editor, including powerful new tools to select elements and forward DOM information to the agent. Learn more about using the browser.

Improved Code Review

It's now easier to view all changes from Agent across multiple files without needing to jump between individual files.

Sandboxed Terminals (GA)

Launched in beta in 1.7, sandboxed terminals are now GA for macOS. We now run agent commands in the secure sandbox by default on macOS with 2.0.

Shell commands (that are not already allowlisted) will automatically run in a sandbox with read/write access to your workspace and no internet access. Learn more about sandboxing.

Team Commands

Define custom commands and rules for your Team in the Cursor dashboard.

This context will then be automatically applied to all members of your team, without needing to store the files in your editor locally, and centrally managed by team admins.

Voice Mode

Control Agent with your voice using built-in speech-to-text conversion. You can also define custom submit keywords in settings to trigger the agent to begin running.

Improved Performance

Cursor uses Language Server Protocols (LSPs) for language-specific features like go to definition, hover tooltips, diagnostics, and more.

We've drastically improved the performance of loading and using LSPs for all languages. This is particularly noticeable when working with agent and viewing diffs.

Python and TypeScript LSPs now are faster by default for large projects with higher memory limits dynamically configured based on available RAM.

We've also fixed a number of memory leaks and improved overall memory usage.

Plan Mode in Background

Create your plan with one model and build the plan with another. You can choose to build the plan in the foreground or background, or even plan with parallel agents to have multiple plans to review.

Shareable Team Commands

Share custom rules, commands, and prompts with your entire team. Create deeplinks through the Cursor Docs.

Improved Prompt UI

Files and directories are now shown inline as pills. We've also improved copy/pasting prompts with tagged context.

We've removed many explicit items in the context menu, including @Definitions, @Web, @Link, @Recent Changes, @Linter Errors, and others. Agent can now self-gather context without needing to manually attach it in the prompt input.

Improved Agent Harness

We've greatly improved the underlying harness for working with Agent across all models. This has notable quality improvements, especially for GPT-5 Codex.

Cloud Agents

Cloud agents now offer 99.9% reliability, instant startup, and a new UI coming soon. We've also improved the experience of sending agents to the cloud from the editor.

Cursor for Enterprise

Sandboxed Terminals: Admin Controls

Enterprise can now enforce standard settings for Sandboxed Terminals across their team. Configure sandbox availability, git access, and network access at the team level.

Hooks: Cloud Distribution

Enterprise teams can now distribute hooks directly from the web dashboard. Admins can add new hooks, save drafts, and select which hooks should apply to which operating systems.

Audit Log

View a timestamped log of admin events in Cursor: user access, setting changes, Team Rule edits, and member management events.

  • Optimized text parsing for chat rendering.
  • Increased default memory for TypeScript language server.
  • Simplified text rendering within chat to use the LSP less.
  • Simplified rendering within worktrees to use a simpler LSP.
  • Simplified the agent to use the LSP less when reading files.
  • Optimized findFiles performance to batch concurrent calls at bounded concurrency.
  • Notepads have been deprecated.
  • Background Agents have been renamed to Cloud Agents.

  • 2.0.1-2.0.28: Bug fixes