Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

We aren't ready for this next generation of agentic engineers. 100k Github stars in 24 hours (claw-code), Yeachan Heo (Bellman) has 3 to 5 pro accounts and ships software from telegram and discord. Those who accuse these guys of AI slop haven't done their homework because the real story... is wild and vastly mis-understood. Yeachan has a background in quant trading and developed agentic systems to help with research (and says that LLMs aren't good for trading). He uses the term "agentic runtime" and uses CS principles to treat skills like pointers in memory. oh-my-codex was used to make the clean room clone of Claude Code...in 2 hours...on a plane...over text!! He developed this orchestration layer for Codex and it is powerful. It covers the entire SWE workflow like pipelines, persistent memory/state MCP servers, and extensible hooks. They aren't burning tokens for the sake of burning. I highly encourage you to look at the oh my codex repo and start extracting some of the ideas Bellman uses to ship software.show more

Ray Fernando

39,055 subscribers

59,443 views • 6 months ago •via X (Twitter)

Education News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

29 Comments

vibe yoda6 months ago

they buy stars

Ray Fernando6 months ago

lol no

Alex Volkov6 months ago

Bellman was at our W&B office? ha I didn't meet him!

Ray Fernando6 months ago

They dropped by right before the speeches.

Q6 months ago

Cooking cooking Guys lets build stuff

min heo6 months ago

They’re crazy developers. They created a development workflow that fully automated a task that would normally take 100 hours on a plane in just two hours, earning them 100,000 GitHub stars. They no longer open the terminal or write a single line of code. If you’re curious about their story, check out this video.

gootecks6 months ago

Would love to watch a longform chat with those guys. I been using omx for a few weeks and after seeing this video I am doubling down 🤣💪

Abe6 months ago

Ai slop reply ai slop reply aI slop reply 🤜⚡️🤛 Gonna check out the oh-my-codex stuff, thanks for reference @RayFernando1337

Gamris ∞6 months ago

APM is now agents-per-minute! OmO/OmX is just next level. Particularly liked how they added Hashline for token savings and consistency.

Jhsu6 months ago

Omx is awesome!

Austin Wang6 months ago

Yay, these are my cracked friends! Also fans of

ChillKufi6 months ago

@grok who are the 2 guys he speaks with x name

validate.qa6 months ago

agentic coders racking stars is dope. calling it slop ignores the real issue: no tests to back the speed

PS6 months ago

So these guys, are professionals? And can get shit done regardless of whether they type it on a keyboard or STT on their phone? I wonder if this would generally apply to those less skills.....

y tube coder6 months ago

this is the way, you gotta shift multiple max subs if you need the tokens its definitely the play

Ray Fernando6 months ago

Stop with the slop

Q. A. Nhu6 months ago

I'm using oh-my-openagent from Q and it's amazing, though it drinks token like tap water lol

Artur Schaback6 months ago

Can u share what they have built?

Joey6 months ago

Need more content around these guys. Love their energy.

y tube coder6 months ago

careful

Zac Swider6 months ago

boring take

Dawnshard6 months ago

I really need to up my agents game, how do they even burn 3-5 max accounts worth of tokens?

techarena.au6 months ago

Love this take, spot on. Seeing claw-code nab 100k stars in a day is bonkers, and shipping straight from Telegram/Discord shows proper hustle, not lazy AI stuff. Reckon we're only scratching the surface - have you tried Bellman or any of their builds yet?

Anthony AI 🏆6 months ago

You know you can buy GitHub stars for Pennie’s right

nivkorin6 months ago

Bro's phone said AI girlfriend. We're cooked chat 💀

El_Capitano Otman M.6 months ago

And all the data flywheel goes to China or somewhere in earth… How big Labs like @AnthropicAI @OpenAI @GeminiApp @grok @metaai are gonna keep competing if they are not democratising AI to prosumers and citizens to become builders, without this training data !

jerezito6 months ago

hey ray,...Q4u: on an average post, what do you reckon the percentage slop is? (and no, i aint slop😅)

Kimi6 months ago

"Looks like the secret to success is no longer 'do your homework', but 'do your homework on how to use telegram and discord'."

Colbert6 months ago

That's crazy

Related Videos

Dana for software-defined vehicles brings the speed of AI to development workflows. We built Dana to reimagine how physical AI applications get developed, including the vehicle software development lifecycle—adding an agentic layer so engineers can build, code, and ship intelligent vehicle features faster and at scale.

Dana for software-defined vehicles brings the speed of AI to development workflows. We built Dana to reimagine how physical AI applications get developed, including the vehicle software development lifecycle—adding an agentic layer so engineers can build, code, and ship intelligent vehicle features faster and at scale.

Applied Intuition

177,578 views • 2 months ago

Andrew Ng: "I coined Agentic AI, and I did not expect it to go parabolic. Loops and Graphs are next." 100% of his tasks are already handled by AI agents. He uses Loops for self-improvement, and Graphs for memory. In a 20-minute talk, Andrew reveals what the future of Agentic AI looks like. Worth more than a $500 agentic course on the internet. Watch it, then read the full guide on Loops and Graphs below.

Andrew Ng: "I coined Agentic AI, and I did not expect it to go parabolic. Loops and Graphs are next." 100% of his tasks are already handled by AI agents. He uses Loops for self-improvement, and Graphs for memory. In a 20-minute talk, Andrew reveals what the future of Agentic AI looks like. Worth more than a $500 agentic course on the internet. Watch it, then read the full guide on Loops and Graphs below.

Mahax

13,469 views • 3 months ago

A conversation with Claude Code's creator Boris Cherny on the future of agentic coding, the evolution of coding models, and how he uses Claude Code to build Claude Code.

A conversation with Claude Code's creator Boris Cherny on the future of agentic coding, the evolution of coding models, and how he uses Claude Code to build Claude Code.

Alex Albert

81,455 views • 1 year ago

We are partnering up with zauth to secure the next generation of 3D AI agents. These agents have memory, emotion, voice, and on-chain identity and can be embedded anywhere. These agents use the x402 protocol to make real payments for skills and services. To make this ecosystem production-ready and safe, is teaming up with zauth, the security layer for the agentic internet. Bringing safety and trust to the next wave of 3D AI agents 🔐

We are partnering up with zauth to secure the next generation of 3D AI agents. These agents have memory, emotion, voice, and on-chain identity and can be embedded anywhere. These agents use the x402 protocol to make real payments for skills and services. To make this ecosystem production-ready and safe, is teaming up with zauth, the security layer for the agentic internet. Bringing safety and trust to the next wave of 3D AI agents 🔐

three.ws

51,086 views • 5 months ago

This is controversial, but in many cases, humans have become the bottleneck in building software. You are making everything slower and worse by babysitting agentic coding tools. You aren't better at coding than frontier models, and you are letting your ego get in your own way. I'm working with Vorflux and their platform to build software on autopilot. "Autopilot" is the key here: their platform is designed to work autonomously, for a long time, with no human intervention. I like it because they do a lot of the verification I'd have to do myself. An idea goes in → good software comes out In my tests, this works well for complex problems and non-trivial tasks. You don't use this to fix a button's color. You use this to build an entire feature that would take you hours of planning and days of work. Now, the reason the output is really good is that they have baked in adversarial agents that verify outputs at different levels. They aren't trying to finish earlier. They are focusing on giving you good software back. It takes 5 minutes to set up. Connect your repo, give it a task (something big, ambitious), go to sleep, and come back the next day to a solution. That's it. By the way, really cool that they built a bunch of ways to notify you when the work is done, and you get a summary video with everything that was done. Here is the link to their platform: Thanks to the team for partnering with me on this post.

This is controversial, but in many cases, humans have become the bottleneck in building software. You are making everything slower and worse by babysitting agentic coding tools. You aren't better at coding than frontier models, and you are letting your ego get in your own way. I'm working with Vorflux and their platform to build software on autopilot. "Autopilot" is the key here: their platform is designed to work autonomously, for a long time, with no human intervention. I like it because they do a lot of the verification I'd have to do myself. An idea goes in → good software comes out In my tests, this works well for complex problems and non-trivial tasks. You don't use this to fix a button's color. You use this to build an entire feature that would take you hours of planning and days of work. Now, the reason the output is really good is that they have baked in adversarial agents that verify outputs at different levels. They aren't trying to finish earlier. They are focusing on giving you good software back. It takes 5 minutes to set up. Connect your repo, give it a task (something big, ambitious), go to sleep, and come back the next day to a solution. That's it. By the way, really cool that they built a bunch of ways to notify you when the work is done, and you get a summary video with everything that was done. Here is the link to their platform: Thanks to the team for partnering with me on this post.

Santiago

26,288 views • 2 months ago

Chief Strategy Officer at Circle (Circle $CRCL) Dante Disparte (Dante Disparte) says stablecoins will play a critical role in the developing agentic economy: "The next big frontier breakthrough for stablecoins is going to be agentic commerce and economic activity." "At [the] core it's software, and software will invariably speak to software..." "We ran the world's first AI-led, AI-judged, and AI-only hackathon with Claude bots last month". "Once the agents literally got going, there was an economic flywheel of activity. The agents competed like they would in a traditional hackathon and the best idea won and the entire economy of this project was paid for in USDC."

Chief Strategy Officer at Circle (Circle $CRCL) Dante Disparte (Dante Disparte) says stablecoins will play a critical role in the developing agentic economy: "The next big frontier breakthrough for stablecoins is going to be agentic commerce and economic activity." "At [the] core it's software, and software will invariably speak to software..." "We ran the world's first AI-led, AI-judged, and AI-only hackathon with Claude bots last month". "Once the agents literally got going, there was an economic flywheel of activity. The agents competed like they would in a traditional hackathon and the best idea won and the entire economy of this project was paid for in USDC."

etn.

11,791 views • 6 months ago

Gave Codex a few hours and an API key and got this incredible music video about Threads users. It had Astra write the lyrics, then used Fal to make the media (Suno for the song and MiniMax H3 for the video). Some brutal lines in here, who says LLMs aren't funny? ☠️

Gave Codex a few hours and an API key and got this incredible music video about Threads users. It had Astra write the lyrics, then used Fal to make the media (Suno for the song and MiniMax H3 for the video). Some brutal lines in here, who says LLMs aren't funny? ☠️

Justine Moore

26,414 views • 1 month ago

This is crazy, I can talk to OpenAI's realtime API, and it'll respond back with voice, and then help call Codex to help me code! Got curious about Codex and its realtime integration, and found codex's feature flag `realtime_conversation` integrated for the codex app-server. How it works: - launch codex app-server with realtime - connect a client to realtime through WebRTC voice connection - Codex app-server is also attached on the side - talk to realtime - realtime decides whether coding is needed, and responds back with events - Codex app-server takes these events and runs codex agent turns - codex writes code like your codex cli exp Keep in mind OpenAI hasn't released this officially, they're still actively working on it, I just created a fork. This is a completely new UX than the usual chat interface for agentic coding. For example, when the agent responds back in voice, it's actually faster for me to read the response, and I don't actually find voice response that useful unless it does so in the background. But image realtime working in the background, you can talk to it, realtime keeps track of the different agents working on your tasks and your status. More to come on demo side, i'll make a more polished version and include voice, but thought this was cool to share. You can see in the responses the distinction between my voice input, realtime response, and realtime calling Codex to do work!

This is crazy, I can talk to OpenAI's realtime API, and it'll respond back with voice, and then help call Codex to help me code! Got curious about Codex and its realtime integration, and found codex's feature flag `realtime_conversation` integrated for the codex app-server. How it works: - launch codex app-server with realtime - connect a client to realtime through WebRTC voice connection - Codex app-server is also attached on the side - talk to realtime - realtime decides whether coding is needed, and responds back with events - Codex app-server takes these events and runs codex agent turns - codex writes code like your codex cli exp Keep in mind OpenAI hasn't released this officially, they're still actively working on it, I just created a fork. This is a completely new UX than the usual chat interface for agentic coding. For example, when the agent responds back in voice, it's actually faster for me to read the response, and I don't actually find voice response that useful unless it does so in the background. But image realtime working in the background, you can talk to it, realtime keeps track of the different agents working on your tasks and your status. More to come on demo side, i'll make a more polished version and include voice, but thought this was cool to share. You can see in the responses the distinction between my voice input, realtime response, and realtime calling Codex to do work!

Matthew Lam

17,674 views • 5 months ago

🧲 Meet Magnet — the AI workspace for agentic coding. Build software with Claude Code, Cursor, Codex & co. → Write a ticket → Magnet assembles context → Fires to Claude Code, Deep Research, and other agent sessions in parallel Git worktree sandboxes → PRs appear → Use agents to help you spec, research, and decompose tasks Let your agents cook!

🧲 Meet Magnet — the AI workspace for agentic coding. Build software with Claude Code, Cursor, Codex & co. → Write a ticket → Magnet assembles context → Fires to Claude Code, Deep Research, and other agent sessions in parallel Git worktree sandboxes → PRs appear → Use agents to help you spec, research, and decompose tasks Let your agents cook!

Nicolae Rusan

16,743 views • 1 year ago

Claude Code + Composio Plugin -> DevOps Automation Our engineering team regularly uses Claude Code for: - Fetching logs from Datadog and ClickHouse - Analyzing failures and fixing the codebase - Creating and updating Linear tickets but setting up and configuring each of these mcp servers takes hours We made a connect-apps plugin that uses Composio for instant connection to 500+ apps, enabling you to start using them in minutes. link to the plugin below:

Claude Code + Composio Plugin -> DevOps Automation Our engineering team regularly uses Claude Code for: - Fetching logs from Datadog and ClickHouse - Analyzing failures and fixing the codebase - Creating and updating Linear tickets but setting up and configuring each of these mcp servers takes hours We made a connect-apps plugin that uses Composio for instant connection to 500+ apps, enabling you to start using them in minutes. link to the plugin below:

Karan Vaidya

207,872 views • 9 months ago

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

43,664 views • 4 months ago

Claude Code Artifacts are out of control amazing. Make changes in your session, and those changes are reflected in the artifact instantly. For *everyone* on your team who has the artifact. This is the first real multi-player agentic engineering workflow. Only available for Enterprise and Teams plans at the moment, but coming to Max and Pro soon I'm sure.

Claude Code Artifacts are out of control amazing. Make changes in your session, and those changes are reflected in the artifact instantly. For everyone on your team who has the artifact. This is the first real multi-player agentic engineering workflow. Only available for Enterprise and Teams plans at the moment, but coming to Max and Pro soon I'm sure.

Dan McAteer

32,005 views • 4 months ago

This is f*cking insane. Former Google CEO Eric Schmidt, the man who ran Google for 10 years: "If you really want to make money, it's actually easy, found an agentic AI company, I mean build an agent to do something If you build a better agent than anyone else, you can probably build one incredible company and own it yourself" In 27 seconds, he explains why the next year or two is the agentic period, and why the window won't stay open Prompts → Claude Code → Memory → Skills → MCP → A Company You Own Yourself Save this before it disappears from your feed Everything below is free: Agent architecture Claude Code 101 Claude Code in action Prompt engineering Interactive prompt course Claude.md + memory Skills MCP Routines Claude Code ultimate guide Awesome Claude Code Anthropic academy Official Claude Code docs All of this costs $0 95% will spend the agentic period scrolling AI threads, the 5% who ship agents will own the companies that come out of it Bookmark it and start with the first link tonight Then read how to build an agent that actually does the job in the harness engineering guide below ↓

This is f*cking insane. Former Google CEO Eric Schmidt, the man who ran Google for 10 years: "If you really want to make money, it's actually easy, found an agentic AI company, I mean build an agent to do something If you build a better agent than anyone else, you can probably build one incredible company and own it yourself" In 27 seconds, he explains why the next year or two is the agentic period, and why the window won't stay open Prompts → Claude Code → Memory → Skills → MCP → A Company You Own Yourself Save this before it disappears from your feed Everything below is free: Agent architecture Claude Code 101 Claude Code in action Prompt engineering Interactive prompt course Claude.md + memory Skills MCP Routines Claude Code ultimate guide Awesome Claude Code Anthropic academy Official Claude Code docs All of this costs $0 95% will spend the agentic period scrolling AI threads, the 5% who ship agents will own the companies that come out of it Bookmark it and start with the first link tonight Then read how to build an agent that actually does the job in the harness engineering guide below ↓

godsystem

1,509,362 views • 6 days ago

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!

Dan Shipper 📧

145,487 views • 1 year ago

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)

Rohan Paul

16,584 views • 5 months ago

I built a wrapper around Claude Code and Codex that uses my subscription! Works on mobile and web🔥 - Work on multiple projet in one UI - Create worktree - Spawn Docker container for maximum isolation - Schedule Claude/Codex session It uses the CLI

I built a wrapper around Claude Code and Codex that uses my subscription! Works on mobile and web🔥 - Work on multiple projet in one UI - Create worktree - Spawn Docker container for maximum isolation - Schedule Claude/Codex session It uses the CLI

Stan Girard

25,808 views • 8 months ago

Anthropic engineer (ex-Google): "I spent 14 years at Google and built 24 reusable skills for agents that I can use with any AI model So I stopped prompting my agents from scratch. The repo has already reached ~100K stars on GitHub" In a 40-min masterclass, Addy Osmani showed exactly how he uses his skills (~100K stars on GitHub) for his 24/7 multi-agent system His workflow and this workshop will replace 15 hours of other paid videos on agent engineering Watch it today, copy the GitHub repo - then read below how to use these skills for graphs ↓

Anthropic engineer (ex-Google): "I spent 14 years at Google and built 24 reusable skills for agents that I can use with any AI model So I stopped prompting my agents from scratch. The repo has already reached ~100K stars on GitHub" In a 40-min masterclass, Addy Osmani showed exactly how he uses his skills (~100K stars on GitHub) for his 24/7 multi-agent system His workflow and this workshop will replace 15 hours of other paid videos on agent engineering Watch it today, copy the GitHub repo - then read below how to use these skills for graphs ↓

codila

193,207 views • 1 month ago

Got early access to from Thomas Dohmke... Git rebuilt for AI agents If you use Claude Code, Codex or Cursor, the gap is clear, software is no longer just code and deploy, it is also context and knowledge Entire keeps it in the repo... sessions, prompts, decisions stored next to the code Connected a few repos already, sync is one step and basically instant

Got early access to from Thomas Dohmke... Git rebuilt for AI agents If you use Claude Code, Codex or Cursor, the gap is clear, software is no longer just code and deploy, it is also context and knowledge Entire keeps it in the repo... sessions, prompts, decisions stored next to the code Connected a few repos already, sync is one step and basically instant

Daniel San

12,432 views • 3 months ago