You can now launch Background Agents directly from Slack by mentioning @Cursor. Agents can read the thread, understand what’s going on, and create PRs in GitHub, all without leaving the conversation.
Cursor reads the entire Slack thread before starting, so Background Agents understand the full context when you reference previous discussions or issues.
You can also ask Cursor to investigate issues and get answers:
To use Background Agents in Slack, an admin needs to set up the integration first. Check out our setup documentation or ask your workspace admin to connect Cursor from the Dashboard → Integrations page.
Once connected, try it in any channel with @Cursor and write a prompt. Use the command help to see all commands, or settings to configure your default model, repo, and branch.
This release brings Bugbot for code review, a first look at memories, one-click MCP setup, Jupyter support, and general availability of Background Agent.
Bugbot automatically reviews your PRs and catches potential bugs and issues.
When an issue is found, Bugbot leaves a comment on your PRs in GitHub. You can click “Fix in Cursor” to move back to the editor with a pre-filled prompt to fix the issue.
To set it up, follow instructions in our Bugbot docs.
Since we released Background Agent, our remote coding agent, in early access a few weeks ago, early signals have been positive.
We’re now excited to expand Background Agent to all users! You can start using it right away by clicking the cloud icon in chat or hitting Cmd/Ctrl+E if you have privacy mode disabled. For users with privacy mode enabled, we’ll soon have a way to enable it for you too!
Cursor can now implement changes in Jupyter Notebooks!
Agent will now create and edit multiple cells directly inside of Jupyter, a significant improvement for research and data science tasks. Only supported with Sonnet models to start.
With Memories, Cursor can remember facts from conversations and reference them in the future. Memories are stored per project on an individual level, and can be managed from Settings.
We’re rolling out Memories as a beta feature. To get started, enable from Settings → Rules.
You can now set up MCP servers in Cursor with one click, and together with OAuth support, you can easily authenticate servers that support it.
We’ve curated a short list of official MCP servers you can add to Cursor at docs.cursor.com/tools.
If you’re an MCP developer, you can easily make your server available to developers by adding a Add to Cursor button in your documentation and READMEs. Generate one at docs.cursor.com/deeplinks.
Cursor can now render visualizations inside of a conversation. In particular, Mermaid diagrams and Markdown tables can now be generated and viewed in the same place!
The setting and dashboard page have gotten some polish with this release.
With the new Dashboard, you can view your individual or team’s usage analytics, update your display name, and view detailed statistics broken down by tool or model.
Introducing unified request-based pricing, Max Mode for all top models, and Background Agent for parallel task execution. Plus, improved context management with @folders support, refreshed Inline Edit with new options, faster file edits, multi-root workspace support, and enhanced chat features including export and duplication.
We’ve heard your feedback and are rolling out a unified pricing model to make it less confusing. Here’s how it works:
All model usage is now unified into request-based pricing
Max mode now uses token-based pricing (similar to how models API pricing works)
Premium tool calls and long context mode are removed to keep it simple
Quotas on plans Hobby, Pro and Business has not changed and slow requests are still included in the plans. All usage can be found in your dashboard to help you track and manage your spend.
Max Mode is now available for all state-of-the-art models in Cursor, with a simpler token-based pricing model. It’s designed to give you full control when you need it most. You can enable it from the model picker to see which models support it. When new models roll out, Max Mode will be how we deliver their full capabilities from day one.
It’s ideal for your hardest problems when you need more context, intelligence and tool use. For everything else, normal mode is still recommended with the same capabilities you’re used to.
The pricing is straightforward: you’re charged based on token usage. If you’ve used any CLI-based coding tool, Max mode will feel like that — but right in Cursor.
Note: If you’re using an older version of Cursor, you’ll still have access to the previous MAX versions and long context mode for a few weeks. However, these features will be sunset soon, so we recommend updating to continue using these capabilities.
We’ve trained a new Tab model that now can suggest changes across multiple files. The model excels particularly at refactors, edit chains, multi file changes, and jumping between related code. You’ll also notice it feels more natural and snappier in day-to-day use.
With this we’ve also added syntax highlighting to the completion suggestions.
In early preview, rolling out gradually: Cursor agents can now run in the background! To try it, head to Settings > Beta > Background Agent.
This allows you to run many agents in parallel and have them tackle bigger tasks. The agents run in their own remote environments. At any point, you can view the status, send a follow-up, or take over.
We’re curious to hear what you think. While it is still early, we’ve found background agents useful internally for fixing nits, doing investigations, and writing first drafts of medium-sized PRs. Read more at docs.cursor.com/background-agent.
You can now use @folders to add your entire codebase into context, just make sure to enable Full folder contents from settings. If a folder (or file) is too large to be included, you’ll see a small icon on the context pill indicating this.
Inline Edit (Cmd/Ctrl+K) has gotten a UI refresh and new options for full file edits (⌘⇧⏎) and sending to agent (⌘L)
Full file makes it easy to do scope changes to a file without using agent. However, you might come across cases where you’re working with a piece of code you want to make multi-file edits to or simply just want more control you can get from agent. That’s when you want to send selected codeblock to agent and keep on editing from there.
We’ve added a new tool to the agent that will search & replace code in files, making it much more efficient for long files. Instead of reading the complete file, Agent can now find the exact place where edits should occur and change only that part. Here's an example editing a file in Postgres codebase where using search & replace tool is nearly double as fast. We’re rolling this out to Anthropic models first and will expand to other models soon.
Now you can create multi-root workspaces to make multiple codebases available to Cursor. All of them will be indexed and available to Cursor, ideal when you have projects in different folders you want to work on in the same space.
Exploring different paths from a conversation while preserving the existing is now possible with chat duplication. Go to a message and start a new chat from the three dots menu.
You can now generate rules directly from a conversation using the /Generate Cursor Rules command. This is useful when you want to capture the existing context of a conversation to reuse later.
For Auto Attached rules with path patterns defined, Agent will now automatically apply the right rules when reading or writing files
We’ve also fixed a long-standing issue where Always attached rules now persist across longer conversations. Agent can now also edit rules reliably.
Chat history has moved into the command palette. You can access it from the “Show history button” in Chat as well as through the Show Chat History command.
Reviewing agent generated code is now easier with a built-in diff view at the end of each conversation. You’ll find the Review changes button at the bottom of chat after a message from the agent.
You can now pass images as part of the context in MCP servers. This helps when screenshots, UI mocks, or diagrams add essential context to a question or prompt.
We’ve added more control for you over terminals started by the agent. Commands can now be edited before they run, or skipped entirely. We’ve also renamed “Pop-out” to “Move to background” to better reflect what it does.
You can now define global ignore patterns that apply across all projects via your user-level settings. This keeps noisy or sensitive files like build outputs or secrets out of prompts, without needing per-project configuration.
We’ve recently added many more models you can use. Try out Gemini 2.5 Pro, Gemini 2.5 Flash, Grok 3, Grok 3 Mini, GPT-4.1, o3 and o4-mini from model settings.
We’re introducing an option to include project structure in context, which adds your directory structure to the prompt. The agent now gets a clearer sense of how your project is organized, which improves suggestions and navigation of large or nested monorepos.
This release introduces chat tabs for parallel conversations, a redesignedmodes system with custom modes, and improvements to cost visibility, indexing performance, and MCP reliability. Additionally, a sound notification plays when a chat is finished.
Agent and Ask modes are the built-in modes in Cursor, now with the option to add custom modes. We’ve also renamed “Edit” to “Manual” to better reflect its behavior.
Ask mode now has access to all search tools by default, so the `@Codebase` tool has been removed. It will automatically search the codebase when needed. If you want to force a search, simply ask Cursor in natural language to “search the codebase”. You can disable search from Ask in the mode menu, which will result in Ask only seeing the context you have provided.
Custom modes (beta) allow you to compose new modes with tools and prompts that fit your workflow. Since custom modes can have custom keybindings, ⌘I will default to Agent mode and ⌘L will toggle the side pane. If you unbind ⌘I, it will also toggle the side pane. Custom modes are currently in beta, and you can enable them from Settings → Features → Chat → Custom modes.
You can also set the default mode from settings (Settings → Features → Chat → Default chat mode) to one of your modes or to the one you used most recently.
Create new tabs (⌘T) in chat to have multiple conversations in parallel. You can also hold Option and click the + button to create a new tab. Cmd+N still creates a new chat in the current tab.
When a tab is awaiting your input, you’ll see an orange dot on that tab.
We’ve made significant improvements to indexing performance of similar codebases within a team, greatly reducing the initial indexing time for subsequent copies of large repositories after one copy has been fully indexed. For example, the Cursor codebase now indexes in under a minute, previously taking around 20 minutes.
We’ve introduced an easier onboarding process to help you get started with Cursor. You’ll be guided through importing settings, selecting themes, keybindings, and other preferences.
You can now launch Background Agents directly from Slack by mentioning @Cursor. Agents can read the thread, understand what’s going on, and create PRs in GitHub, all without leaving the conversation.
Cursor reads the entire Slack thread before starting, so Background Agents understand the full context when you reference previous discussions or issues.
You can also ask Cursor to investigate issues and get answers:
To use Background Agents in Slack, an admin needs to set up the integration first. Check out our setup documentation or ask your workspace admin to connect Cursor from the Dashboard → Integrations page.
Once connected, try it in any channel with @Cursor and write a prompt. Use the command help to see all commands, or settings to configure your default model, repo, and branch.
This release brings Bugbot for code review, a first look at memories, one-click MCP setup, Jupyter support, and general availability of Background Agent.
Bugbot automatically reviews your PRs and catches potential bugs and issues.
When an issue is found, Bugbot leaves a comment on your PRs in GitHub. You can click “Fix in Cursor” to move back to the editor with a pre-filled prompt to fix the issue.
To set it up, follow instructions in our Bugbot docs.
Since we released Background Agent, our remote coding agent, in early access a few weeks ago, early signals have been positive.
We’re now excited to expand Background Agent to all users! You can start using it right away by clicking the cloud icon in chat or hitting Cmd/Ctrl+E if you have privacy mode disabled. For users with privacy mode enabled, we’ll soon have a way to enable it for you too!
Cursor can now implement changes in Jupyter Notebooks!
Agent will now create and edit multiple cells directly inside of Jupyter, a significant improvement for research and data science tasks. Only supported with Sonnet models to start.
With Memories, Cursor can remember facts from conversations and reference them in the future. Memories are stored per project on an individual level, and can be managed from Settings.
We’re rolling out Memories as a beta feature. To get started, enable from Settings → Rules.
You can now set up MCP servers in Cursor with one click, and together with OAuth support, you can easily authenticate servers that support it.
We’ve curated a short list of official MCP servers you can add to Cursor at docs.cursor.com/tools.
If you’re an MCP developer, you can easily make your server available to developers by adding a Add to Cursor button in your documentation and READMEs. Generate one at docs.cursor.com/deeplinks.
Cursor can now render visualizations inside of a conversation. In particular, Mermaid diagrams and Markdown tables can now be generated and viewed in the same place!
The setting and dashboard page have gotten some polish with this release.
With the new Dashboard, you can view your individual or team’s usage analytics, update your display name, and view detailed statistics broken down by tool or model.
Introducing unified request-based pricing, Max Mode for all top models, and Background Agent for parallel task execution. Plus, improved context management with @folders support, refreshed Inline Edit with new options, faster file edits, multi-root workspace support, and enhanced chat features including export and duplication.
We’ve heard your feedback and are rolling out a unified pricing model to make it less confusing. Here’s how it works:
All model usage is now unified into request-based pricing
Max mode now uses token-based pricing (similar to how models API pricing works)
Premium tool calls and long context mode are removed to keep it simple
Quotas on plans Hobby, Pro and Business has not changed and slow requests are still included in the plans. All usage can be found in your dashboard to help you track and manage your spend.
Max Mode is now available for all state-of-the-art models in Cursor, with a simpler token-based pricing model. It’s designed to give you full control when you need it most. You can enable it from the model picker to see which models support it. When new models roll out, Max Mode will be how we deliver their full capabilities from day one.
It’s ideal for your hardest problems when you need more context, intelligence and tool use. For everything else, normal mode is still recommended with the same capabilities you’re used to.
The pricing is straightforward: you’re charged based on token usage. If you’ve used any CLI-based coding tool, Max mode will feel like that — but right in Cursor.
Note: If you’re using an older version of Cursor, you’ll still have access to the previous MAX versions and long context mode for a few weeks. However, these features will be sunset soon, so we recommend updating to continue using these capabilities.
We’ve trained a new Tab model that now can suggest changes across multiple files. The model excels particularly at refactors, edit chains, multi file changes, and jumping between related code. You’ll also notice it feels more natural and snappier in day-to-day use.
With this we’ve also added syntax highlighting to the completion suggestions.
In early preview, rolling out gradually: Cursor agents can now run in the background! To try it, head to Settings > Beta > Background Agent.
This allows you to run many agents in parallel and have them tackle bigger tasks. The agents run in their own remote environments. At any point, you can view the status, send a follow-up, or take over.
We’re curious to hear what you think. While it is still early, we’ve found background agents useful internally for fixing nits, doing investigations, and writing first drafts of medium-sized PRs. Read more at docs.cursor.com/background-agent.
You can now use @folders to add your entire codebase into context, just make sure to enable Full folder contents from settings. If a folder (or file) is too large to be included, you’ll see a small icon on the context pill indicating this.
Inline Edit (Cmd/Ctrl+K) has gotten a UI refresh and new options for full file edits (⌘⇧⏎) and sending to agent (⌘L)
Full file makes it easy to do scope changes to a file without using agent. However, you might come across cases where you’re working with a piece of code you want to make multi-file edits to or simply just want more control you can get from agent. That’s when you want to send selected codeblock to agent and keep on editing from there.
We’ve added a new tool to the agent that will search & replace code in files, making it much more efficient for long files. Instead of reading the complete file, Agent can now find the exact place where edits should occur and change only that part. Here's an example editing a file in Postgres codebase where using search & replace tool is nearly double as fast. We’re rolling this out to Anthropic models first and will expand to other models soon.
Now you can create multi-root workspaces to make multiple codebases available to Cursor. All of them will be indexed and available to Cursor, ideal when you have projects in different folders you want to work on in the same space.
Exploring different paths from a conversation while preserving the existing is now possible with chat duplication. Go to a message and start a new chat from the three dots menu.
You can now generate rules directly from a conversation using the /Generate Cursor Rules command. This is useful when you want to capture the existing context of a conversation to reuse later.
For Auto Attached rules with path patterns defined, Agent will now automatically apply the right rules when reading or writing files
We’ve also fixed a long-standing issue where Always attached rules now persist across longer conversations. Agent can now also edit rules reliably.
Chat history has moved into the command palette. You can access it from the “Show history button” in Chat as well as through the Show Chat History command.
Reviewing agent generated code is now easier with a built-in diff view at the end of each conversation. You’ll find the Review changes button at the bottom of chat after a message from the agent.
You can now pass images as part of the context in MCP servers. This helps when screenshots, UI mocks, or diagrams add essential context to a question or prompt.
We’ve added more control for you over terminals started by the agent. Commands can now be edited before they run, or skipped entirely. We’ve also renamed “Pop-out” to “Move to background” to better reflect what it does.
You can now define global ignore patterns that apply across all projects via your user-level settings. This keeps noisy or sensitive files like build outputs or secrets out of prompts, without needing per-project configuration.
We’ve recently added many more models you can use. Try out Gemini 2.5 Pro, Gemini 2.5 Flash, Grok 3, Grok 3 Mini, GPT-4.1, o3 and o4-mini from model settings.
We’re introducing an option to include project structure in context, which adds your directory structure to the prompt. The agent now gets a clearer sense of how your project is organized, which improves suggestions and navigation of large or nested monorepos.
This release introduces chat tabs for parallel conversations, a redesignedmodes system with custom modes, and improvements to cost visibility, indexing performance, and MCP reliability. Additionally, a sound notification plays when a chat is finished.
Agent and Ask modes are the built-in modes in Cursor, now with the option to add custom modes. We’ve also renamed “Edit” to “Manual” to better reflect its behavior.
Ask mode now has access to all search tools by default, so the `@Codebase` tool has been removed. It will automatically search the codebase when needed. If you want to force a search, simply ask Cursor in natural language to “search the codebase”. You can disable search from Ask in the mode menu, which will result in Ask only seeing the context you have provided.
Custom modes (beta) allow you to compose new modes with tools and prompts that fit your workflow. Since custom modes can have custom keybindings, ⌘I will default to Agent mode and ⌘L will toggle the side pane. If you unbind ⌘I, it will also toggle the side pane. Custom modes are currently in beta, and you can enable them from Settings → Features → Chat → Custom modes.
You can also set the default mode from settings (Settings → Features → Chat → Default chat mode) to one of your modes or to the one you used most recently.
Create new tabs (⌘T) in chat to have multiple conversations in parallel. You can also hold Option and click the + button to create a new tab. Cmd+N still creates a new chat in the current tab.
When a tab is awaiting your input, you’ll see an orange dot on that tab.
We’ve made significant improvements to indexing performance of similar codebases within a team, greatly reducing the initial indexing time for subsequent copies of large repositories after one copy has been fully indexed. For example, the Cursor codebase now indexes in under a minute, previously taking around 20 minutes.
We’ve introduced an easier onboarding process to help you get started with Cursor. You’ll be guided through importing settings, selecting themes, keybindings, and other preferences.
