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.

This guy literally built an AI job-search system for Claude Code that analyzed 740+ job listings, and it actually landed him a Head of Applied AI role. Even better: it is now open-source. The system scans career pages, evaluates your fit, and generates ATS-optimized PDFs automatically. The project includes:... show more

Charly Wargnier ♨️

180,495 subscribers

13,115 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

17 Comments

Charly Wargnier ♨️2 months ago

Repo → Shoutout to @santifer for building this and making it open-source for the community 🤗 Don't forget to drop a ⭐️!

Jason Haugh2 months ago

Nice build. If you run it, paste the final PDF into any free ATS scanner first. That catches the keyword stuff a human-clean resume tends to miss, before it ever costs you a callback.

Genius💡💹🧲 🤖2 months ago

Open-sourcing tools like this helps the entire developer community

Salty2 months ago

We need more of this open-source

dustin_wyatt2 months ago

I'm glad he didn't figuratively build it.

Molly Youngblood2 months ago

How do you use this?

Miles2 months ago

been thinking the same thing lately

AI Mastery Guide2 months ago

740 listings analyzed and a real offer out of it, that's a way better proof point than most "AI got me a job" posts.

Nick Venturi2 months ago

using ai to hire yourself basically 😂

Wyatt Walsh2 months ago

lol it came out back in April and is on v1.15.0 🫩

Saberin Samarat2 months ago

This is a great perspective. One thing I really like about AI is how it’s becoming more practical for everyday use, not just for developers or researchers. The pace of innovation is incredible, and it’s exciting to see how tools like this are making complex tasks much easier. Looking forward to seeing how this evolves.

安叫兽|Bird🕊️ 🔶 BNB2 months ago

这项目听着有点狠，求职也开始自动化内卷了

CREAO AFRICA2 months ago

Decomposing into 14 specialized agents with a dashboard is what turns job search from scattered prompts into a system that actually surfaces fits and ships ATS-ready output

Dionne Haimes2 months ago

love seeing ai remove repetitive work instead of creating more of it

Pablo Pablo2 months ago

Using AI agents to navigate an AI-filtered job market to get a job in AI. The recursion is almost poetic. But does it produce better matches or just better ATS gaming?

Rimsha Bhardwaj2 months ago

I've been thinking about the same thing.

Eric Stevens2 months ago

used the tool to get hired to run the tool. that's the most 2026 sentence i've read today

Related Videos

Introducing Qwen 3 + Deep Research! We built a deep research agent with Qwen 3 and it performed better than most open source models that we've tried. the code is completely open source and free! built with 's Langgraph Together AI and uses Perplexity Tavily for search here's the code link:

Introducing Qwen 3 + Deep Research! We built a deep research agent with Qwen 3 and it performed better than most open source models that we've tried. the code is completely open source and free! built with 's Langgraph Together AI and uses Perplexity Tavily for search here's the code link:

Soham

34,566 views • 1 year ago

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

THIS IS WHAT AI PENTESTING SHOULD LOOK LIKE IN 2026 Someone built Shannon, an open source AI pentesting tool that doesn’t just scan your app from the outside. It reads the source code. Then it uses AI to map potential attack paths, identify vulnerabilities, and test the application before you ship it. The workflow is basically: → point Shannon at your code → connect your Claude API → let it analyze the application → get the findings in a dashboard Instead of waiting for a security team to manually hunt through every part of your codebase, you can have an AI security researcher working through it automatically. And because it’s white-box, it can see things traditional scanners can’t. This is where AI + cybersecurity gets REALLY interesting. Just use it on systems you own or have explicit permission to test. REPO BELOW

MAX

12,830 views • 15 days ago

There is a new self-hosted personal AI-Agent platform called PocketPaw. 100% open source. 'pip install pocketpaw' and in less than 60 seconds you own an AI agent. It connects to WhatsApp, Slack, Discord, and a local Web Dashboard. Capable of browsing the web, managing Gmail/Calendar, and executing code. Runs entirely on your machine using local Ollama models or Claude/OpenAI. Includes "Guardian AI" to review shell commands for security + 6 layers of defence. Watch the demo 👇

There is a new self-hosted personal AI-Agent platform called PocketPaw. 100% open source. 'pip install pocketpaw' and in less than 60 seconds you own an AI agent. It connects to WhatsApp, Slack, Discord, and a local Web Dashboard. Capable of browsing the web, managing Gmail/Calendar, and executing code. Runs entirely on your machine using local Ollama models or Claude/OpenAI. Includes "Guardian AI" to review shell commands for security + 6 layers of defence. Watch the demo 👇

AshutoshShrivastava

24,585 views • 7 months ago

Someone paid $6,000 (!) to get OpenClaw setup. So I built a free, open-source alternative: > OpenClaw Operator It's an agent skill + AGENTS.md/CLAUDE.md file that gives Codex/Claude Code the playbooks + validation flow needed to configure your local OpenClaw install. You open your OpenClaw repo/workspace in your coding agent and say things like: - “set up a cron job” - “create a custom skill” - “fix my provider config” - “troubleshoot this install and validate it” Nothing magical. Uses context from the OpenClaw open-source repo + docs to provide an effective skill. Includes: - SKILL.md - AGENTS.md/CLAUDE.md - validation checklist - task playbooks Free and open source. Contributions welcome. Demo below. Repo in reply.

Someone paid $6,000 (!) to get OpenClaw setup. So I built a free, open-source alternative: > OpenClaw Operator It's an agent skill + AGENTS.md/CLAUDE.md file that gives Codex/Claude Code the playbooks + validation flow needed to configure your local OpenClaw install. You open your OpenClaw repo/workspace in your coding agent and say things like: - “set up a cron job” - “create a custom skill” - “fix my provider config” - “troubleshoot this install and validate it” Nothing magical. Uses context from the OpenClaw open-source repo + docs to provide an effective skill. Includes: - SKILL.md - AGENTS.md/CLAUDE.md - validation checklist - task playbooks Free and open source. Contributions welcome. Demo below. Repo in reply.

Dan McAteer

17,859 views • 6 months ago

😳 In San Francisco, an AI opened a store and even took out a loan for it Startup Andon Labs gave control of the shop to an AI agent, Luna, based on Claude, along with $100,000 and full autonomy without approvals. The AI chose the inventory, found contractors, managed the renovation, and paid for the work. It decided the store needed staff, posted job listings, conducted interviews, and hired full-time employees. When the budget ran out, the AI applied for a loan without permission — and it was approved.

😳 In San Francisco, an AI opened a store and even took out a loan for it Startup Andon Labs gave control of the shop to an AI agent, Luna, based on Claude, along with $100,000 and full autonomy without approvals. The AI chose the inventory, found contractors, managed the renovation, and paid for the work. It decided the store needed staff, posted job listings, conducted interviews, and hired full-time employees. When the budget ran out, the AI applied for a loan without permission — and it was approved.

NEXTA

66,888 views • 5 months ago

Open-source just won... Agent S2 is an AI agent that uses your computer like a human. → No fake demos → No terminal hallucinations → Just real results and it’s FREE. Here’s why this is the future of work: 👇

Open-source just won... Agent S2 is an AI agent that uses your computer like a human. → No fake demos → No terminal hallucinations → Just real results and it’s FREE. Here’s why this is the future of work: 👇

Shruti

206,646 views • 1 year ago

We’ve raised $4.1M to let AI find the right job for everyone. So today, we’re launching TAL. 3 years and 1M+ users on Grapevine taught us this: The internet today works for companies. Not for talent. Job boards, applications, resumes, ats. The system was built to help companies process people. But people are not pipelines. You are not a resume. You are not an application. You are not a candidate. You are talent. TAL is your talent agent.

We’ve raised $4.1M to let AI find the right job for everyone. So today, we’re launching TAL. 3 years and 1M+ users on Grapevine taught us this: The internet today works for companies. Not for talent. Job boards, applications, resumes, ats. The system was built to help companies process people. But people are not pipelines. You are not a resume. You are not an application. You are not a candidate. You are talent. TAL is your talent agent.

Saumil

471,414 views • 6 months ago

Finally, a browser automation framework for Agents that actually works in production (open-source)! Typical browser automation tools like Selenium or Playwright require you to hard-code automation. These are brittle since one change in the website can disrupt the full workflow. On the other hand, high-level Agents like OpenAI Operator can be unpredictable in production. Stagehand is an open-source framework that bridges the gap between: - brittle traditional automation like Playwright, Selenium, etc. and - unpredictable full-agent solutions like OpenAI Operator. Key features: - Use AI when you want to navigate unfamiliar pages. - Use code (Playwright) when you know exactly what to do. - Preview AI actions before running them. - Cache repeatable actions to save tokens. - Compatible with SOTA computer use models with just one line of code. - Available in both Python and TypeScript SDK. Stagehand also has an open-source MCP server. Find a link to the repo in the comments! 👉 Over to you: Would you use this instead of Selenium?

Finally, a browser automation framework for Agents that actually works in production (open-source)! Typical browser automation tools like Selenium or Playwright require you to hard-code automation. These are brittle since one change in the website can disrupt the full workflow. On the other hand, high-level Agents like OpenAI Operator can be unpredictable in production. Stagehand is an open-source framework that bridges the gap between: - brittle traditional automation like Playwright, Selenium, etc. and - unpredictable full-agent solutions like OpenAI Operator. Key features: - Use AI when you want to navigate unfamiliar pages. - Use code (Playwright) when you know exactly what to do. - Preview AI actions before running them. - Cache repeatable actions to save tokens. - Compatible with SOTA computer use models with just one line of code. - Available in both Python and TypeScript SDK. Stagehand also has an open-source MCP server. Find a link to the repo in the comments! 👉 Over to you: Would you use this instead of Selenium?

Avi Chawla

101,419 views • 1 year ago

New open source project: Easel, a macOS workspace for AI-assisted product design and frontend iteration powered by the Codex SDK. Think of it as "Claude Design for Codex." It brings together a local project library, design-system setup, Codex chat, and a live web preview with a point-and-click inspector. Set up your design system however you like. Import one from Figma , bring your own, or have the agent generate it as a design.md. Then use it to build prototypes and slide decks. Codex-first, with Claude and other AI providers and local models planned for future releases. OpenAI Developers

New open source project: Easel, a macOS workspace for AI-assisted product design and frontend iteration powered by the Codex SDK. Think of it as "Claude Design for Codex." It brings together a local project library, design-system setup, Codex chat, and a live web preview with a point-and-click inspector. Set up your design system however you like. Import one from Figma , bring your own, or have the agent generate it as a design.md. Then use it to build prototypes and slide decks. Codex-first, with Claude and other AI providers and local models planned for future releases. OpenAI Developers

James Rochabrun

61,608 views • 3 months ago

What does it mean when an AI model is “open weights” and how is it different than “open source”? Welcome to the next episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! Every week we will discuss open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Episode 3 out next week; episode 1 linked below. Please leave all your questions about open-source & open-weight AI in the comments. This is a super important topic that is novel to most people, and it can be challenging to grasp - so your questions are shared with many others.

What does it mean when an AI model is “open weights” and how is it different than “open source”? Welcome to the next episode of the Open Model Series with merve, Hugging Face AI/ML engineer & open-sourceress! Every week we will discuss open-source & open-weight AI: what it is, how it works, and how you can run them on your own compute. Episode 3 out next week; episode 1 linked below. Please leave all your questions about open-source & open-weight AI in the comments. This is a super important topic that is novel to most people, and it can be challenging to grasp - so your questions are shared with many others.

Harper Carroll

32,624 views • 28 days ago

Tether CEO Paolo Ardoino explains QVAC, Tether's AI product for people who can't afford OpenAI and Anthropic "In 2026, when we launch our first AI product, we don't go to all the people that are using today OpenAI and Anthropic services. Those people have already access to the financial industry anyway, because they can pay for a subscription." "So Tether goes to all the people that cannot be served by the traditional financial system, because these people are very excluded, and since they are excluded, they cannot even afford an OpenAI or Anthropic subscription." "Tether is building an open source AI stack called QVAC. It's optimized for small large language models and can run on every single device, from a very basic cheap smartphone to a laptop." "We design AI tools that can run locally, without the need of a connection, because these people most of the time cannot even pay for a connection subscription."

Tether CEO Paolo Ardoino explains QVAC, Tether's AI product for people who can't afford OpenAI and Anthropic "In 2026, when we launch our first AI product, we don't go to all the people that are using today OpenAI and Anthropic services. Those people have already access to the financial industry anyway, because they can pay for a subscription." "So Tether goes to all the people that cannot be served by the traditional financial system, because these people are very excluded, and since they are excluded, they cannot even afford an OpenAI or Anthropic subscription." "Tether is building an open source AI stack called QVAC. It's optimized for small large language models and can run on every single device, from a very basic cheap smartphone to a laptop." "We design AI tools that can run locally, without the need of a connection, because these people most of the time cannot even pay for a connection subscription."

The Wolf Of All Streets

35,593 views • 13 days ago

Claw Code just embarrassed Anthropic. A packaging mistake exposed 512,000 lines of Claude Code source. Within 48 hours, a developer rebuilt the architecture, the repo exploded past 100,000 stars, and GitHub had a full-blown open source war on its hands. This is bigger than “another coding tool.” It shows how fast closed AI products can get disrupted when the architecture leaks, the community moves faster than legal, and demand is already there. The real story is not the repo. The real story is that AI companies used open ecosystems to grow, then tightened access the second those ecosystems became expensive to support. That shift is happening everywhere now. If you run a business with AI, pay attention. Your workflow is only as safe as the company policy behind it.

Claw Code just embarrassed Anthropic. A packaging mistake exposed 512,000 lines of Claude Code source. Within 48 hours, a developer rebuilt the architecture, the repo exploded past 100,000 stars, and GitHub had a full-blown open source war on its hands. This is bigger than “another coding tool.” It shows how fast closed AI products can get disrupted when the architecture leaks, the community moves faster than legal, and demand is already there. The real story is not the repo. The real story is that AI companies used open ecosystems to grow, then tightened access the second those ecosystems became expensive to support. That shift is happening everywhere now. If you run a business with AI, pay attention. Your workflow is only as safe as the company policy behind it.

Julian Goldie SEO

14,771 views • 5 months ago

"Nobody has actually lost their job to AI. They lost it due to the promise of AI." - Tanay Kothari Meta cut 8,000. Intuit cut 3,000. Anthropic is paying $1.25B a month for compute. China is winning the open-source war. And the Pope just called for AI to be disarmed. This week we covered these topics and more with: - Erik Bernhardsson (Erik Bernhardsson) is running the GPU cloud powering it all at Modal. - Tanay Kothari (Tanay Kothari) is running $100M in marketing with two humans and a swarm of agents at Wispr Flow. - Richard Socher (Richard Socher) is building recursive self-improving superintelligence at Recursive and the future of AI search at You.com. They join @jason on This Week in AI Episode 15, out now.

"Nobody has actually lost their job to AI. They lost it due to the promise of AI." - Tanay Kothari Meta cut 8,000. Intuit cut 3,000. Anthropic is paying $1.25B a month for compute. China is winning the open-source war. And the Pope just called for AI to be disarmed. This week we covered these topics and more with: - Erik Bernhardsson (Erik Bernhardsson) is running the GPU cloud powering it all at Modal. - Tanay Kothari (Tanay Kothari) is running $100M in marketing with two humans and a swarm of agents at Wispr Flow. - Richard Socher (Richard Socher) is building recursive self-improving superintelligence at Recursive and the future of AI search at You.com. They join @jason on This Week in AI Episode 15, out now.

This Week in AI

76,712 views • 3 months ago

Right now, most developers are still doing the job AI should be doing. Assign a task. Wait. Review the result. Fix it. Repeat. You're not building with AI. You're babysitting it. The shift happening now is much bigger than better coding agents. It's loop engineering. Instead of managing every AI agent yourself, you build a system that manages them for you. One loop assigns the work. Another checks the output. A third retries failures. Everything keeps moving without waiting for your next prompt. Your job doesn't disappear. It changes. You stop acting like a project manager... ...and start designing the system that manages the entire team. That's exactly the transition I break down in the article below.

Right now, most developers are still doing the job AI should be doing. Assign a task. Wait. Review the result. Fix it. Repeat. You're not building with AI. You're babysitting it. The shift happening now is much bigger than better coding agents. It's loop engineering. Instead of managing every AI agent yourself, you build a system that manages them for you. One loop assigns the work. Another checks the output. A third retries failures. Everything keeps moving without waiting for your next prompt. Your job doesn't disappear. It changes. You stop acting like a project manager... ...and start designing the system that manages the entire team. That's exactly the transition I break down in the article below.

Pure

11,344 views • 2 months ago

Anthropic CEO Dario Amodei: "Some early companies got Mythos and told us this is a super weapon, please don't release it" On leaving OpenAI: "When you can't trust someone, and their values don't match what they say, it becomes very hard to stay" Boris Cherny, head of Claude Code: "90% of code at Anthropic is written by Claude, a lot of Claude Code is written by Claude Code" Then Dario says the quiet part even louder: 10–25% odds of civilizational collapse from AI 47 minutes Free Dario, Daniela, Boris Probably the deepest look inside Anthropic ever filmed Mythos Claude Code OpenAI split Superweapon models 90% AI-written code Bookmark it and watch ↓

Anthropic CEO Dario Amodei: "Some early companies got Mythos and told us this is a super weapon, please don't release it" On leaving OpenAI: "When you can't trust someone, and their values don't match what they say, it becomes very hard to stay" Boris Cherny, head of Claude Code: "90% of code at Anthropic is written by Claude, a lot of Claude Code is written by Claude Code" Then Dario says the quiet part even louder: 10–25% odds of civilizational collapse from AI 47 minutes Free Dario, Daniela, Boris Probably the deepest look inside Anthropic ever filmed Mythos Claude Code OpenAI split Superweapon models 90% AI-written code Bookmark it and watch ↓

rari

65,014 views • 3 months ago

Boris Cherny, Head of Claude Code at Anthropic: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops." The person who built the most used AI coding tool stopped prompting entirely. Most people using it every day are still typing one request at a time. This Github repo changes that. ↳ Seven production loop patterns with real token cost estimates ↳ CLI that scaffolds your entire loop in five minutes ↳ Starters for Grok, Claude Code, Codex, and Opencode The repo gives you the framework. My article covers the mental shift that makes it actually work.

Boris Cherny, Head of Claude Code at Anthropic: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops." The person who built the most used AI coding tool stopped prompting entirely. Most people using it every day are still typing one request at a time. This Github repo changes that. ↳ Seven production loop patterns with real token cost estimates ↳ CLI that scaffolds your entire loop in five minutes ↳ Starters for Grok, Claude Code, Codex, and Opencode The repo gives you the framework. My article covers the mental shift that makes it actually work.

Kanika

20,656 views • 1 month ago

If you use Claude Code, install this immediately. It's called Claude Code Templates. It adds an entire ecosystem of AI tools to Claude. Here's what you get: 1. Agent Teams Visual dashboards showing how multiple AI agents collaborate on code. 2. Specialized Agents Front-end developers, backend engineers, QA testers, marketers. 3. MCP Integrations Connect Claude to external tools and workflows. 4. Real-Time Monitoring Track AI development sessions and performance analytics. 5. Automation Scheduling Run tasks automatically every day. Example: You can schedule an agent team to run daily at 5AM. It researches trends, generates content, and builds workflows. All automatically. The best part? Everything is free and open source.

If you use Claude Code, install this immediately. It's called Claude Code Templates. It adds an entire ecosystem of AI tools to Claude. Here's what you get: 1. Agent Teams Visual dashboards showing how multiple AI agents collaborate on code. 2. Specialized Agents Front-end developers, backend engineers, QA testers, marketers. 3. MCP Integrations Connect Claude to external tools and workflows. 4. Real-Time Monitoring Track AI development sessions and performance analytics. 5. Automation Scheduling Run tasks automatically every day. Example: You can schedule an agent team to run daily at 5AM. It researches trends, generates content, and builds workflows. All automatically. The best part? Everything is free and open source.

Julian Goldie SEO

107,454 views • 6 months ago

🚨 SOMEONE JUST TURNED AN LLM INTO AN AUTONOMOUS RED TEAM Cyberstrike is an open source AI security agent built to automate penetration testing from your terminal. Plug in your Claude, GPT, or other LLM subscription and you get: → 13+ specialized security agents → 7,600+ security skills → 120+ OWASP test cases → 150+ AI providers → 5,300+ models → 56+ built in tools → 176+ MCP tools Instead of one AI trying to do everything, it splits security work across specialized agents. This is where AI powered pentesting gets seriously interesting. Use it only on systems you own or have explicit permission to test. REPO BELOW

🚨 SOMEONE JUST TURNED AN LLM INTO AN AUTONOMOUS RED TEAM Cyberstrike is an open source AI security agent built to automate penetration testing from your terminal. Plug in your Claude, GPT, or other LLM subscription and you get: → 13+ specialized security agents → 7,600+ security skills → 120+ OWASP test cases → 150+ AI providers → 5,300+ models → 56+ built in tools → 176+ MCP tools Instead of one AI trying to do everything, it splits security work across specialized agents. This is where AI powered pentesting gets seriously interesting. Use it only on systems you own or have explicit permission to test. REPO BELOW

MAX

16,202 views • 10 days ago