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。

executor now has a desktop app! add whatever MCPs / OpenAPIs / GraphQL servers you want once and then every agent can use them converts them all into code mode under the hood, so you can have thousands of tools and no context bloat everything stays 100% local on... show more

Rhys

56,543 subscribers

44,324 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I'm now building Executor full time as a startup! The state of tool calling is a mess: - Everyone is using different agents - You have no idea what actions are going to run - Destructive actions are treated the same as normal Executor lets you set up everything once & use it with any agent. You're able to control what tools can be called, require approval on destructive actions, and invite your team to all use them. Under the hood, it's built on codemode to let you add thousands of tools with 0 context bloat. I've been using it for a month so far and it has completely changed how I interact with agents. There's so much to be built here, immediately next up on the roadmap is workspaces, skills, workflows, and generative ui. Everything is being built open source over at there's a lot more coming on an SDK to embed it into your own agents, a self hostable cloud app, and plugins There's an early beta version over at It's very early on - if you hit any bugs let me know and I'll get them fixed up, excited to share more as I build it!

I'm now building Executor full time as a startup! The state of tool calling is a mess: - Everyone is using different agents - You have no idea what actions are going to run - Destructive actions are treated the same as normal Executor lets you set up everything once & use it with any agent. You're able to control what tools can be called, require approval on destructive actions, and invite your team to all use them. Under the hood, it's built on codemode to let you add thousands of tools with 0 context bloat. I've been using it for a month so far and it has completely changed how I interact with agents. There's so much to be built here, immediately next up on the roadmap is workspaces, skills, workflows, and generative ui. Everything is being built open source over at there's a lot more coming on an SDK to embed it into your own agents, a self hostable cloud app, and plugins There's an early beta version over at It's very early on - if you hit any bugs let me know and I'll get them fixed up, excited to share more as I build it!

Rhys

219,080 次观看 • 1 个月前

Building AI agents and tools is getting ridiculously easy! Here is a pretty impressive FREE and Open-Source AI agent builder that runs on your computer. It's a desktop app you can install on Mac or Windows. Link: • Free • 100% no-code: You can type what you want, and the tool will build everything for you. • You can use local models like DeepSeek or Qwen, or connect to cloud models like GPT-4o, Claude, or Gemini with your API key. • You can turn the tools you build into MCP Servers. I recorded a quick video to show you how easy it is to build something from scratch.

Building AI agents and tools is getting ridiculously easy! Here is a pretty impressive FREE and Open-Source AI agent builder that runs on your computer. It's a desktop app you can install on Mac or Windows. Link: • Free • 100% no-code: You can type what you want, and the tool will build everything for you. • You can use local models like DeepSeek or Qwen, or connect to cloud models like GPT-4o, Claude, or Gemini with your API key. • You can turn the tools you build into MCP Servers. I recorded a quick video to show you how easy it is to build something from scratch.

Santiago

56,815 次观看 • 1 年前

Claude Code can now connect to remote MCP servers. Pull context from your tools directly into Claude Code with no local setup required.

Claude Code can now connect to remote MCP servers. Pull context from your tools directly into Claude Code with no local setup required.

Anthropic

540,303 次观看 • 1 年前

You can now upload images in the VibeCode app. You can use them as icons, logos, backgrounds, and more in any mobile app you Vibe Code on your phone.

You can now upload images in the VibeCode app. You can use them as icons, logos, backgrounds, and more in any mobile app you Vibe Code on your phone.

vibecode.dev

29,504 次观看 • 1 年前

Your entire creative workflow just collapsed into one infinite canvas. In Grok Imagine Agent Mode, you can brainstorm, write, generate and edit images, then turn them into videos without leaving the page. Try it at on desktop.

Your entire creative workflow just collapsed into one infinite canvas. In Grok Imagine Agent Mode, you can brainstorm, write, generate and edit images, then turn them into videos without leaving the page. Try it at on desktop.

Grok Imagine

72,553,212 次观看 • 1 个月前

How to create a surreal oner with Runway. First, shoot your scene. Then cut each moment into a 5 second export. Bring each clip into Runway and use Aleph to transform them however you like - add things, remove things, relight your scene. Once you have all of your shots, bring them all back together on your timeline. Add sound design and you're done. Try it today on web and the Runway iOS app.

How to create a surreal oner with Runway. First, shoot your scene. Then cut each moment into a 5 second export. Bring each clip into Runway and use Aleph to transform them however you like - add things, remove things, relight your scene. Once you have all of your shots, bring them all back together on your timeline. Add sound design and you're done. Try it today on web and the Runway iOS app.

Runway

10,582 次观看 • 9 个月前

You can now have an AI agent in your mobile operating system. Here are 3 things it can do: 1. Hook into system-level triggers like notifications 2. Use any app that's already installed on the device 3. Read data and gather context across sandboxed applications

You can now have an AI agent in your mobile operating system. Here are 3 things it can do: 1. Hook into system-level triggers like notifications 2. Use any app that's already installed on the device 3. Read data and gather context across sandboxed applications

Sam Hall

155,241 次观看 • 2 年前

Using skills with lots of tool calls or research? In Visual Studio Code, you can now run skills in a dedicated sub agent so your main chat context stays clean and focused ⚡

Using skills with lots of tool calls or research? In Visual Studio Code, you can now run skills in a dedicated sub agent so your main chat context stays clean and focused ⚡

Visual Studio Code

18,380 次观看 • 26 天前

Comment “MCP” and I’ll DM you the servers I use every day Browser MCP tests apps for you, Magic MCP builds UI in seconds, and GitMCP links your AI to any repo. These are only 3 of the seven MCPs I use. Once you try them, you’ll never want to build with AI without them.

Comment “MCP” and I’ll DM you the servers I use every day Browser MCP tests apps for you, Magic MCP builds UI in seconds, and GitMCP links your AI to any repo. These are only 3 of the seven MCPs I use. Once you try them, you’ll never want to build with AI without them.

Prajwal Tomar

19,080 次观看 • 9 个月前

Introducing vision mode: now your coding agent can take screenshots and record videos of your web app! In the demo below, we asked Tidewave to implement a feature, record videos of the feature working on both desktop and mobile resolutions, and deliver them to Slack.

Introducing vision mode: now your coding agent can take screenshots and record videos of your web app! In the demo below, we asked Tidewave to implement a feature, record videos of the feature working on both desktop and mobile resolutions, and deliver them to Slack.

José Valim

11,884 次观看 • 2 个月前

We've brought Claude Code to our Desktop app. You can now easily run multiple Claude Code sessions locally or in the cloud and switch between them.

We've brought Claude Code to our Desktop app. You can now easily run multiple Claude Code sessions locally or in the cloud and switch between them.

Anthony Morris ツ

468,181 次观看 • 6 个月前

Tired of manually approving agent mode tools? You can configure the setting to auto-approve all tools. And you can configure this setting only for your remote development environment, for some level of protection from any potentially destructive actions.

Tired of manually approving agent mode tools? You can configure the setting to auto-approve all tools. And you can configure this setting only for your remote development environment, for some level of protection from any potentially destructive actions.

Visual Studio Code

26,604 次观看 • 1 年前

BlackBird now captures all your meetings and remembers every conversation, entirely on your device. Your personal model keeps everything private and local, so you can revisit any discussion, find key insights, and ask questions anytime, privately & offline! Download here: Completely local, no privacy compromised! The future of AI is here!!

BlackBird now captures all your meetings and remembers every conversation, entirely on your device. Your personal model keeps everything private and local, so you can revisit any discussion, find key insights, and ask questions anytime, privately & offline! Download here: Completely local, no privacy compromised! The future of AI is here!!

Decompute AI

87,002 次观看 • 1 年前

ok, this is kind of incredible - all the benefits of CLIs while keeping the approval flow of tool calling same concept as Cloudflare's Code Mode, where the agent is writing typescript the agent generates: await tools.calendar.update({ ... }); under the hood, that blocks until the tool has been approved, and then you can define which tools require approval vs which don't

ok, this is kind of incredible - all the benefits of CLIs while keeping the approval flow of tool calling same concept as Cloudflare's Code Mode, where the agent is writing typescript the agent generates: await tools.calendar.update({ ... }); under the hood, that blocks until the tool has been approved, and then you can define which tools require approval vs which don't

Rhys

47,593 次观看 • 4 个月前

You can now see a breakdown of your agent's context usage in Cursor 3.3. Use these stats to diagnose context issues and improve your setup across rules, skills, MCPs, and subagents.

You can now see a breakdown of your agent's context usage in Cursor 3.3. Use these stats to diagnose context issues and improve your setup across rules, skills, MCPs, and subagents.

Cursor

199,857 次观看 • 1 个月前

Crazy idea: Vibe code apps with MCPs. Use an agent for one-offs, then codify common flows into internal tools. Just vibe coded a YouTube transcript-to-Notion app – MCPs are already authed, so it just works!

Crazy idea: Vibe code apps with MCPs. Use an agent for one-offs, then codify common flows into internal tools. Just vibe coded a YouTube transcript-to-Notion app – MCPs are already authed, so it just works!

Sawyer Hood

14,049 次观看 • 1 年前

I can smell this video. 💯 If you have tools like this from your late father or grandfather, please use them. They wouldn't want them to just sit in that box forever. I have all of my grandpa’s tools and use them frequently, even though I have my own box full of tools. 💔

I can smell this video. 💯 If you have tools like this from your late father or grandfather, please use them. They wouldn't want them to just sit in that box forever. I have all of my grandpa’s tools and use them frequently, even though I have my own box full of tools. 💔

👉M-Û-R-Č-H👈

18,703 次观看 • 2 个月前

130+ skills are now built into your Superagent. Some are ready to use, and some can be created based on what you need. Add a skill once, and your Superagent can use it as part of your workflows. Stack skills, connect tools, and build flows that run end-to-end.

130+ skills are now built into your Superagent. Some are ready to use, and some can be created based on what you need. Add a skill once, and your Superagent can use it as part of your workflows. Stack skills, connect tools, and build flows that run end-to-end.

Base44

1,856,460 次观看 • 2 个月前

We have 12 examples for Supabase Realtime on our Realtime landing page! From syncing positions of 3d objects to a collaborative whiteboard, you can find inspiration on how to use Supabase for your next app! All source codes are available, so you can drop them into your app!

We have 12 examples for Supabase Realtime on our Realtime landing page! From syncing positions of 3d objects to a collaborative whiteboard, you can find inspiration on how to use Supabase for your next app! All source codes are available, so you can drop them into your app!

Tyler Shukert

12,752 次观看 • 5 个月前

I tested Gemini 3.1 Flash Live and one thing stood out immediately: the speed. You ask a question. It answers almost instantly. No awkward delay. No clunky back-and-forth. Then it gets more interesting. You can: use voice mode, use webcam mode, share your screen, connect tools, add system instructions, and publish the app to the cloud. So this is not just “voice chat with AI.” It is the beginning of real-time AI agents you can actually ship.

I tested Gemini 3.1 Flash Live and one thing stood out immediately: the speed. You ask a question. It answers almost instantly. No awkward delay. No clunky back-and-forth. Then it gets more interesting. You can: use voice mode, use webcam mode, share your screen, connect tools, add system instructions, and publish the app to the cloud. So this is not just “voice chat with AI.” It is the beginning of real-time AI agents you can actually ship.

Julian Goldie SEO

21,000 次观看 • 2 个月前