正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Background Agent (Preview) "a remote, asynchronous agent that runs outside the main Cursor editor in a remote containerized environment. It allows you to offload long-running or complex task" works best for tasks that require less human interaction like fixing simple bugs, small features, or long changes more information about... show more

Melvin Vivas

21,937 subscribers

81,372 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

13 条评论

Melvin Vivas 的头像

Melvin Vivas1 年前

cursor v0.50 is here lots of juicy features here's all the features you need to know 🧵 👇

Melvin Vivas 的头像

Melvin Vivas1 年前

Simpler, unified pricing for @cursor_ai – All model usage now on request-based pricing – Max Mode adopts token-based pricing (like model APIs) – Premium tool calls & long context mode removed

Melvin Vivas 的头像

Melvin Vivas1 年前

Max Mode for all top models (token-based) max mode is ideal for harder problems which require more context, intelligence and tool use @cursor_ai

Melvin Vivas 的头像

Melvin Vivas1 年前

Include your entire codebase in context use @ folders to add your entire codebase into context @cursor_ai

Melvin Vivas 的头像

Melvin Vivas1 年前

Inline Edit(Cmd/Ctrl+K) Refresh Supports full file edits. Full file edits makes it easy to do scope changes to a file without using agent You can also send the code block to the agent for multi-file edits @cursor_ai

Melvin Vivas 的头像

Melvin Vivas1 年前

Fast edits for long files with Agent Agent can now find the exact place where edits should occur and change only that part @cursor_ai

Melvin Vivas 的头像

Melvin Vivas1 年前

Workspaces Work across multiple codebases in one session

Melvin Vivas 的头像

Melvin Vivas1 年前

Exporting Chat You can now export chats to a markdown file. This is useful when you want to get advise from other AI about your code using the conversation you already have with @cursor_ai

Melvin Vivas 的头像

Melvin Vivas1 年前

Duplicate Chat Useful when you want to fork a chat and explore different options @cursor_ai

Melvin Vivas 的头像

Melvin Vivas1 年前

like this update? support me by reposting this thread 👇 you can also follow me @donvito for more AI

Melvin Vivas 的头像

Melvin Vivas1 年前

FYI, this is dropping in cursor 0.50 as well — added after I posted this thread Tab to edit other files — perfect for refactoring Tab suggestions also now have syntax highlighting!

Melvin Vivas 的头像

Melvin Vivas1 年前

Here's how you enable Background Agents

MightyBot 的头像

MightyBot1 年前

🧠 Unified Search. Smarter Meetings. Effortless CRM. MightyBot is your AI agent platform for seamless workflows—record meetings, automate CRM updates, and find answers across apps in seconds. 🌟 Focus on what matters. We'll handle the grind.

相关视频

You can now delegate tasks to Cursor directly from Notion. It's built on the Cursor SDK, so every cloud agent runs on the same models, harness, and runtime that power Cursor. @Cursor on any spec or assign it a task to open a PR your whole team can review.

You can now delegate tasks to Cursor directly from Notion. It's built on the Cursor SDK, so every cloud agent runs on the same models, harness, and runtime that power Cursor. @Cursor on any spec or assign it a task to open a PR your whole team can review.

Cursor

316,245 次观看 • 1 个月前

🚨 Cursor for writing is here! 📝 Meet the HyperWrite document editor. A next-gen agent-driven editor that: - Searches + writes naturally - Applies changes for you - Incredible autocomplete as you type - Generates rewrites - Pulls in your relevant docs How to try it:

🚨 Cursor for writing is here! 📝 Meet the HyperWrite document editor. A next-gen agent-driven editor that: - Searches + writes naturally - Applies changes for you - Incredible autocomplete as you type - Generates rewrites - Pulls in your relevant docs How to try it:

Matt Shumer

66,785 次观看 • 1 年前

cursor continues to curate the most frictionless way to build software. - planned a new app idea with Cursor Agent (Laptop) - left cafe for gym so i hand off to Cloud Agent (Cloud) - mid workout, i get an msg that my PR is done (Email) - mid pump, i get a new idea. message Cursor via iphone to add it - monday morning comes. i already forgot about my app - cursor emails me w/ a 30 sec demo of agent clicking through the core feature. shows me that it works if you showed me this in 2022, i would have put my life savings into cursor stock immediately

cursor continues to curate the most frictionless way to build software. - planned a new app idea with Cursor Agent (Laptop) - left cafe for gym so i hand off to Cloud Agent (Cloud) - mid workout, i get an msg that my PR is done (Email) - mid pump, i get a new idea. message Cursor via iphone to add it - monday morning comes. i already forgot about my app - cursor emails me w/ a 30 sec demo of agent clicking through the core feature. shows me that it works if you showed me this in 2022, i would have put my life savings into cursor stock immediately

shawn

13,058 次观看 • 3 个月前

Anthropic is rolling out Dispatch, a major new update for Claude Cowork that turns your mobile phone into a remote control for your desktop AI agent. Currently in research preview, this feature allows you to assign complex, multi-step tasks to Claude while you are away from your keyboard, and it will execute them using your computer's local resources.

Anthropic is rolling out Dispatch, a major new update for Claude Cowork that turns your mobile phone into a remote control for your desktop AI agent. Currently in research preview, this feature allows you to assign complex, multi-step tasks to Claude while you are away from your keyboard, and it will execute them using your computer's local resources.

Wes Roth

13,251 次观看 • 4 个月前

Cursor for video editing is here. The new Underlord agent from is insanely good at automating edits. Upload a clip and describe what you want changed - like "cut out pauses and filler words" or "add captions." The agent does it for you. A quick example 👇

Cursor for video editing is here. The new Underlord agent from is insanely good at automating edits. Upload a clip and describe what you want changed - like "cut out pauses and filler words" or "add captions." The agent does it for you. A quick example 👇

Justine Moore

36,635 次观看 • 1 年前

I think I finally found the sweet spot for long-running AI coding tasks: GLM 4.7 feels like Sonnet, costs ~20× less, and runs forever without melting your budget. Pair it with a good agent setup and it quietly does real work.

I think I finally found the sweet spot for long-running AI coding tasks: GLM 4.7 feels like Sonnet, costs ~20× less, and runs forever without melting your budget. Pair it with a good agent setup and it quietly does real work.

Mervin Praison

98,539 次观看 • 7 个月前

Last, but not least, don't sleep on this one: Le Chat now has Work mode (Preview) — a powerful agent for complex long-horizon tasks like research, analysis, and actions across your connected tools. Connectors are on by default so the agent pulls context from docs, email, and calendars as it works, and sessions persist across many turns until the task is complete.

Last, but not least, don't sleep on this one: Le Chat now has Work mode (Preview) — a powerful agent for complex long-horizon tasks like research, analysis, and actions across your connected tools. Connectors are on by default so the agent pulls context from docs, email, and calendars as it works, and sessions persist across many turns until the task is complete.

Mistral Vibe

32,521 次观看 • 3 个月前

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

Santiago

17,438 次观看 • 28 天前

Agent mode is now available in public preview for all users in Visual Studio 17.14. Agent mode in Visual Studio allows you to define tasks using natural language, with Copilot autonomously planning, editing your codebase, invoking tools, and iterating to resolve issues. Unlike Copilot Chat or Edits, agent mode doesn’t stop at one suggestion or file edit. Read more about it in our blog. 📖 #visualstudionews #githubcopilot #agent

Agent mode is now available in public preview for all users in Visual Studio 17.14. Agent mode in Visual Studio allows you to define tasks using natural language, with Copilot autonomously planning, editing your codebase, invoking tools, and iterating to resolve issues. Unlike Copilot Chat or Edits, agent mode doesn’t stop at one suggestion or file edit. Read more about it in our blog. 📖 #visualstudionews #githubcopilot #agent

Visual Studio

93,267 次观看 • 1 年前

AI should 10× your shipping speed not 10× your prompt count. Meet Traycer: a planning layer that drafts a per-file blueprint, then hands exact tasks to Cursor, Windsurf, or Claude Code. Less noise, more code. Here’s how it works (with demos): 👇

AI should 10× your shipping speed not 10× your prompt count. Meet Traycer: a planning layer that drafts a per-file blueprint, then hands exact tasks to Cursor, Windsurf, or Claude Code. Less noise, more code. Here’s how it works (with demos): 👇

Shruti

36,424 次观看 • 1 年前

Replicas is a background coding agent that lives in sandboxed VMs and works like a teammate: it runs codebases locally with all your dependencies and tooling, iterates until it's satisfied, and opens a PR. Delegate to it from Slack, Linear, or GitHub. Congrats on the launch, Connor Loi!

Replicas is a background coding agent that lives in sandboxed VMs and works like a teammate: it runs codebases locally with all your dependencies and tooling, iterates until it's satisfied, and opens a PR. Delegate to it from Slack, Linear, or GitHub. Congrats on the launch, Connor Loi!

Y Combinator

22,245 次观看 • 3 个月前

Sick of Cursor mess up your code? This new flow reduced 90% error for my Cursor - by adopting a task system: 1. Break down PRD into small tasks with dependencies 2. Maintain & update task list as we go 3. Self improve with cursor rules With tools like claude task master & Boomerang tasks, this process is a no brainer I broken down my step by step process in the video If you want to learn more about vibe coding beyond basics, join my community here: (also get free access to 10xCoder.Dev)

Sick of Cursor mess up your code? This new flow reduced 90% error for my Cursor - by adopting a task system: 1. Break down PRD into small tasks with dependencies 2. Maintain & update task list as we go 3. Self improve with cursor rules With tools like claude task master & Boomerang tasks, this process is a no brainer I broken down my step by step process in the video If you want to learn more about vibe coding beyond basics, join my community here: (also get free access to 10xCoder.Dev)

Jason Zhou

43,014 次观看 • 1 年前

working with cloud agents in cursor feels the same as local, but the fact that i can shut down my computer and still have it running is amazing. one of my favorite use cases is planning in cursor, then send off to cloud agent for impl. here's a short demo

working with cloud agents in cursor feels the same as local, but the fact that i can shut down my computer and still have it running is amazing. one of my favorite use cases is planning in cursor, then send off to cloud agent for impl. here's a short demo

eric zakariasson

61,940 次观看 • 9 个月前

we are working on OpenControl - a library that uses AI to finally solve the headache of internal tooling idea is simple - define a set of tools in code that can reference functions from your codebase or anywhere else these tools get deployed to your infra (runs anywhere, lambda, worker, containers, etc) and exposes a protocol that allows clients like cursor, claude-code, etc to use them they can orchestrate tasks like "can you reset the password of anyone who hasn't logged in a year" demo below and details on how it works in the thread

we are working on OpenControl - a library that uses AI to finally solve the headache of internal tooling idea is simple - define a set of tools in code that can reference functions from your codebase or anywhere else these tools get deployed to your infra (runs anywhere, lambda, worker, containers, etc) and exposes a protocol that allows clients like cursor, claude-code, etc to use them they can orchestrate tasks like "can you reset the password of anyone who hasn't logged in a year" demo below and details on how it works in the thread

dax

109,046 次观看 • 1 年前

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,109 次观看 • 1 年前

Introducing Jules, an AI coding agent powered by Gemini 2.5 Pro. Jules works asynchronously across your repo on tasks like fixing bugs or refactoring, helping you cross multiple things off your to do list at the same time. Plus, stay updated with Codecasts, a daily podcast of your repo's recent commits. Try it for free, globally, at

Introducing Jules, an AI coding agent powered by Gemini 2.5 Pro. Jules works asynchronously across your repo on tasks like fixing bugs or refactoring, helping you cross multiple things off your to do list at the same time. Plus, stay updated with Codecasts, a daily podcast of your repo's recent commits. Try it for free, globally, at

Jules

409,994 次观看 • 1 年前