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。

pull requests are getting harder to keep up with as agents write more code Mainframe now turns any GitHub PR into a narrated video walkthrough so you can understand what changed without starting from the raw diff try it at

Jordan Singer

179,226 subscribers

79,470 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

30 条评论

Jordan Singer 的头像

Jordan Singer3 个月前

here's an example of @vinvan's PR to add a feedback form to videos

Jordan Singer 的头像

Jordan Singer3 个月前

when you connect your GitHub to Mainframe, new pull requests marked ready for review get a link at the top and a check for the status of your video

Jordan Singer 的头像

Jordan Singer3 个月前

swap out github dot com with for any PR link to give it a try on one of your pull requests

Jordan Singer 的头像

Jordan Singer3 个月前

and join our Discord to get early access to our upcoming Mainframe TestFlight beta where you can watch your videos on the go

Jordan Singer 的头像

Jordan Singer3 个月前

try Mainframe for free to generate videos of your PRs or give your agent the MCP to watch your agents work

saint laurent del rey 的头像

saint laurent del rey3 个月前

@mainframe next: tiktok for PRs

Jordan Singer 的头像

Jordan Singer3 个月前

@mainframe

Spencer Schoeben 的头像

Spencer Schoeben3 个月前

@mainframe we tried this early today and loved it. can’t wait to use it more. great stuff

Jordan Singer 的头像

Jordan Singer3 个月前

@mainframe glad to hear!

Ian Tracey 的头像

Ian Tracey3 个月前

@mainframe This is super cool @jsngr and team!

Jake Go 的头像

Jake Go3 个月前

@mainframe wow that’s incredible

Ryan Hoover 的头像

Ryan Hoover2 个月前

@mainframe Chain all of these together and you have an end of week changelog/show and tell for the whole team :)

Dan Nelson 的头像

Dan Nelson3 个月前

@mainframe Nice. The number of times me and @ow have quickly approved PRs for simple internal tool fixes is… a lot. Definitely need a way to understand what has changed, just without seriously slowing us down. This seems great.

chriscardoza 的头像

chriscardoza3 个月前

@mainframe wow this is soo cool

𝒎𝒊𝒄𝒉𝒂𝒆𝒍 📟 的头像

𝒎𝒊𝒄𝒉𝒂𝒆𝒍 📟3 个月前

@mainframe need to add a subway surfers split screen

Lorenz Wöhr 的头像

Lorenz Wöhr3 个月前

@mainframe I'll only watch it if it's @fireship_dev-paced ~ % npx skills add lorenzwoehr/share-video

Jordan Singer 的头像

Jordan Singer3 个月前

@mainframe @fireship_dev nice! able to turn the video link publicly accessible?

Srini 的头像

Srini3 个月前

@mainframe Wow! 😀

Andrei J. Luca 的头像

Andrei J. Luca3 个月前

@mainframe Sick! Off topic: what browser is that? Is it Dia or Zen?

sam 的头像

sam3 个月前

@mainframe THIS IS FUCKING SICKKKK

Bodunde Tejumola 的头像

Bodunde Tejumola3 个月前

@mainframe <3333

Boris 的头像

Boris3 个月前

@mainframe Hey where did we hear this before? 🤔 @frainpan

Maliyia Kardun 的头像

Maliyia Kardun2 个月前

@mainframe PR review bottlenecks are killing velocity as AI-generated code scales , we're tackling it from a different angle with narrated video walkthroughs of diffs, curious if that maps to anything you're seeing on your end.

スディプト的头像

スディプト3 个月前

@mainframe please bring back the old mainframe website 😭

Luiz Ottino 的头像

Luiz Ottino3 个月前

@mainframe Very very very very cool! I will def will try it later today.

Nattu 的头像

Nattu3 个月前

@mainframe Definitely going to give this a try.

JFire 的头像

JFire3 个月前

@mainframe Yooo bro ! Do well to check your inbox and your gmail . I sent a proposal that you might want to look at

Chris Liu 的头像

Chris Liu3 个月前

@mainframe This is great. Better to render the test page with the new feature.

Nick Venturi 的头像

Nick Venturi3 个月前

@mainframe we really created bots to write code just to watch videos of what they did

Tomas Ward 的头像

Tomas Ward3 个月前

@mainframe nice!

相关视频

Temporal CEO Samar Birwadker says GitHub was designed for humans, but is now at the mercy of agents. "Agents are starting to get more and more long-lived, more asynchronous, and more mission-critical." "For example, if you pick coding agents alone, is something like GitHub was designed for humans collaborate and create [pull requests] right now." "Now a lot of code is being generated by these agents, and they're the ones creating these PRs essentially, and even code review process is being automated by other agents." "So now this entire system backend, which is being built for human consumption, is now at the mercy of these agents kind of using it for their own coordination and collaboration."

Temporal CEO Samar Birwadker says GitHub was designed for humans, but is now at the mercy of agents. "Agents are starting to get more and more long-lived, more asynchronous, and more mission-critical." "For example, if you pick coding agents alone, is something like GitHub was designed for humans collaborate and create [pull requests] right now." "Now a lot of code is being generated by these agents, and they're the ones creating these PRs essentially, and even code review process is being automated by other agents." "So now this entire system backend, which is being built for human consumption, is now at the mercy of these agents kind of using it for their own coordination and collaboration."

MTS

26,902 次观看 • 4 个月前

You can now fix PRs without leaving Devin Review! Just ask Devin to fix any issues it found. Devin will propose inline code changes that you can apply with a single click. Swap github -> devinreview in any PR link to try Devin Review, no account needed.

You can now fix PRs without leaving Devin Review! Just ask Devin to fix any issues it found. Devin will propose inline code changes that you can apply with a single click. Swap github -> devinreview in any PR link to try Devin Review, no account needed.

Cognition

34,966 次观看 • 7 个月前

Claude Code just got a lot easier to use 🙌 Just updated You can now install agents, commands, MCPs, and templates with a single command. Click on any card and it gives you the exact line to run. Everything is pulled from GitHub, the site runs on GitHub Pages, and downloads are logged with GitHub Actions.

Claude Code just got a lot easier to use 🙌 Just updated You can now install agents, commands, MCPs, and templates with a single command. Click on any card and it gives you the exact line to run. Everything is pulled from GitHub, the site runs on GitHub Pages, and downloads are logged with GitHub Actions.

Daniel San

135,292 次观看 • 1 年前

Claude Code Routines are here! In addition to a schedule, you can now trigger templated agents via GitHub event or API – with our infra & your MCP+repos They've changed how we do docs, backlog maintenance and more internally at Anthropic Get started at

Claude Code Routines are here! In addition to a schedule, you can now trigger templated agents via GitHub event or API – with our infra & your MCP+repos They've changed how we do docs, backlog maintenance and more internally at Anthropic Get started at

Noah Zweben

598,937 次观看 • 5 个月前

I just made a walkthrough on how to turn any video library into a searchable, chat-ready AI tutor it can: – find answers instantly without scrubbing through hours of video – show you the exact video & timestamp the answer came from – understand what’s happening on-screen visually, not just the audio reply “video” and I’ll DM you the walkthrough (must be following)

I just made a walkthrough on how to turn any video library into a searchable, chat-ready AI tutor it can: – find answers instantly without scrubbing through hours of video – show you the exact video & timestamp the answer came from – understand what’s happening on-screen visually, not just the audio reply “video” and I’ll DM you the walkthrough (must be following)

Tyler

21,412 次观看 • 1 年前

pr reviews with Tembo are on another level. this isn't static diff analysis. every pr gets its own vm, runs with any agent you choose, and reviews your code like a real engineer would. fully customizable instructions, plus the ability to pull in sentry or any other context. this is what agentic pr reviews were supposed to be.

pr reviews with Tembo are on another level. this isn't static diff analysis. every pr gets its own vm, runs with any agent you choose, and reviews your code like a real engineer would. fully customizable instructions, plus the ability to pull in sentry or any other context. this is what agentic pr reviews were supposed to be.

benja

13,624 次观看 • 9 个月前

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Santiago

64,438 次观看 • 9 个月前

Hello! Today we're releasing Paper Desktop Paper is now a canvas for Cursor, Claude Code, Codex. Any agent can read and write html to Paper. • push or pull from your codebase • pull real data from anywhere • less work, more design What will you ship? Sound on 🎶

Hello! Today we're releasing Paper Desktop Paper is now a canvas for Cursor, Claude Code, Codex. Any agent can read and write html to Paper. • push or pull from your codebase • pull real data from anywhere • less work, more design What will you ship? Sound on 🎶

Stephen Haney

1,717,425 次观看 • 7 个月前

"To build a great company, you need to write code and talk to users." - Florian Juengermann (co-founder of Listen Labs) "AI agents can now write code, so what becomes important is building the right thing and having the right feedback." "That's what we are building: telling the AI what to do, what to build, and being the tastemaker."

"To build a great company, you need to write code and talk to users." - Florian Juengermann (co-founder of Listen Labs) "AI agents can now write code, so what becomes important is building the right thing and having the right feedback." "That's what we are building: telling the AI what to do, what to build, and being the tastemaker."

TBPN

15,291 次观看 • 1 年前

Wow. GitHub CEO Thomas Dohmke just announced GitHub Copilot X: - Copilot Chat - "ChatGPT-like experience in your editor" powered by GPT-4 - Copilot for Pull Requests - AI-generated descriptions for pull requests on GitHub - GitHub Copilot for Docs - chat for *any* company's repos and docs, starting with React/Azure/MDN - GitHub Copilot CLI - compose commands and loops, and throw around obscure find flags to satisfy your query. as Benedict Evans might say, the incumbents are embracing and integrating AI into existing form factors faster than startups can build them. To win, startups have to create -new- form factors from first principles.

Wow. GitHub CEO Thomas Dohmke just announced GitHub Copilot X: - Copilot Chat - "ChatGPT-like experience in your editor" powered by GPT-4 - Copilot for Pull Requests - AI-generated descriptions for pull requests on GitHub - GitHub Copilot for Docs - chat for any company's repos and docs, starting with React/Azure/MDN - GitHub Copilot CLI - compose commands and loops, and throw around obscure find flags to satisfy your query. as Benedict Evans might say, the incumbents are embracing and integrating AI into existing form factors faster than startups can build them. To win, startups have to create -new- form factors from first principles.

swyx

2,052,412 次观看 • 3 年前

ChatGPT connecting to external data sources offers a glimpse into what AI interoperability looks like. Ask any question in ChatGPT and it can now pull data from Box. The future of AI is AI Agents that can access your systems and data to complete any task for you.

ChatGPT connecting to external data sources offers a glimpse into what AI interoperability looks like. Ask any question in ChatGPT and it can now pull data from Box. The future of AI is AI Agents that can access your systems and data to complete any task for you.

Aaron Levie

57,745 次观看 • 1 年前

Introducing: product videos that update themselves. Clueso can now automatically update all your product videos every time you ship a change to your product. Whenever your engineering team pushes a release to GitHub: - Clueso scans the PR to understand what changed. - It checks those changes against every video on your website, help center, LMS, and more. - It identifies which videos are outdated and tells you what to update. - On your approval, Clueso Agents open your product and re-record the affected sections while preserving all your previous edits - Finally, publish the updated videos everywhere with the Clueso MCP

Introducing: product videos that update themselves. Clueso can now automatically update all your product videos every time you ship a change to your product. Whenever your engineering team pushes a release to GitHub: - Clueso scans the PR to understand what changed. - It checks those changes against every video on your website, help center, LMS, and more. - It identifies which videos are outdated and tells you what to update. - On your approval, Clueso Agents open your product and re-record the affected sections while preserving all your previous edits - Finally, publish the updated videos everywhere with the Clueso MCP

Akash Anand

19,659 次观看 • 1 个月前

Holy moly Never seen someone being that bullish for AI developement as Dario Amodei: - There's just an exponential just like we had an exponential with Moore's law - I think the models are just going to get more and more capable at everything - I've had internal people at Anthropic say, "I don't write any code anymore. I don't write I don't open up an editor and write code. I just let Claude code write the first draft and and all I do is edit it. - What what we're going to see in the future is just like we've going to be seen in the past except more so - the models are just going to get more and more intellectually capable and you know the the revenue is going to keep adding zeros. holy moly, Dario!

Holy moly Never seen someone being that bullish for AI developement as Dario Amodei: - There's just an exponential just like we had an exponential with Moore's law - I think the models are just going to get more and more capable at everything - I've had internal people at Anthropic say, "I don't write any code anymore. I don't write I don't open up an editor and write code. I just let Claude code write the first draft and and all I do is edit it. - What what we're going to see in the future is just like we've going to be seen in the past except more so - the models are just going to get more and more intellectually capable and you know the the revenue is going to keep adding zeros. holy moly, Dario!

Chubby♨️

77,711 次观看 • 9 个月前

Hermes Desktop just removed the biggest barrier to AI agents. No more terminal. Here’s what changed everything: → You can now run Hermes in a clean Mac app → Edit memory + skills without SSH → Search every past conversation instantly → Run multi-agent workflows visually → Assign tasks like a real team board This turns AI from “tool” → “operator.” Save this video, you’ll finally understand how agents actually work. Want the SOP? DM me. 💬

Hermes Desktop just removed the biggest barrier to AI agents. No more terminal. Here’s what changed everything: → You can now run Hermes in a clean Mac app → Edit memory + skills without SSH → Search every past conversation instantly → Run multi-agent workflows visually → Assign tasks like a real team board This turns AI from “tool” → “operator.” Save this video, you’ll finally understand how agents actually work. Want the SOP? DM me. 💬

Julian Goldie SEO

43,421 次观看 • 4 个月前

We just launched Entire 101, a practical video series for developers building with coding agents. As agents produce more of our code, keeping track of what changed, why it changed, and the work behind those changes matters more than ever. Watch episode 1: How to Enable Entire in Your Repo

We just launched Entire 101, a practical video series for developers building with coding agents. As agents produce more of our code, keeping track of what changed, why it changed, and the work behind those changes matters more than ever. Watch episode 1: How to Enable Entire in Your Repo

Entire

14,052 次观看 • 1 个月前

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The Startup Ideas Podcast (SIP) 🧃

13,666 次观看 • 3 个月前

A senior engineering team costs $500,000 a year to do what these 10 open-source repos give Claude Code for free! Running Claude Code without these repos means using maybe 20% of what it can actually do. Most repos getting hyped right now are noise. These ten were tested, the GitHub numbers were checked, and the setups were documented with the exact install command for each one. No coding required for any of them. Bookmark so you do not lose it! Follow NeilXbt for more Claude content.

A senior engineering team costs $500,000 a year to do what these 10 open-source repos give Claude Code for free! Running Claude Code without these repos means using maybe 20% of what it can actually do. Most repos getting hyped right now are noise. These ten were tested, the GitHub numbers were checked, and the setups were documented with the exact install command for each one. No coding required for any of them. Bookmark so you do not lose it! Follow NeilXbt for more Claude content.

NeilXbt

21,314 次观看 • 2 个月前

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

220,805 次观看 • 4 个月前