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。

php2shell. emudhra. railway. all in one week. if your agents aren't checking your code for vulnerabilities, somebody else will. so we open sourced all the security loops we run at cloudroom (one-click setup) 15% off with code BLACKOCTOBER until oct 31.

Cloudroom

1,326 subscribers

20,807 次观看 • 19 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

3 条评论

Corben Bellamy | S corp & rental tax 的头像

Corben Bellamy | S corp & rental tax18 天前

@bot

Alexo 的头像

Alexo18 天前

@bot

Aapakari 的头像

Aapakari19 天前

does the security loop scan repo-wide or per branch?

相关视频

Last week we made changes to make it easy to get started using OpenCode remotely with Cloud Agents One command setup, across desktop + terminal. Your configs, models, auth, ready to go Try it out: railway code --opencode / --opencode2 docs:

Last week we made changes to make it easy to get started using OpenCode remotely with Cloud Agents One command setup, across desktop + terminal. Your configs, models, auth, ready to go Try it out: railway code --opencode / --opencode2 docs:

Railway

24,158 次观看 • 1 个月前

introducing Cloudroom, the best app for heavy agent use > run Cloud Agents, with any harness > Rust-based core, fully open-source > use your existing subscriptions it works with Codex, Claude Code, Pi, Cursor, OpenCode, fx... this video was built in Cloudroom, with Opus 5.5 go to:

introducing Cloudroom, the best app for heavy agent use > run Cloud Agents, with any harness > Rust-based core, fully open-source > use your existing subscriptions it works with Codex, Claude Code, Pi, Cursor, OpenCode, fx... this video was built in Cloudroom, with Opus 5.5 go to:

David Ondrej

53,703 次观看 • 1 个月前

Big news: Enclave is now open to everyone, and today we're launching Threat Feed. Enclave is an autonomous security team for AI-native companies: a fleet of security agents that test your code, cloud, and infrastructure the way an attacker would. We built it on a simple belief. Attackers already use swarms of cheap AI agents to probe for weaknesses around the clock, so defenders need agents of their own to keep up. A small team without a security function should be able to defend like a large one. Threat Feed is the newest piece: a live feed of new vulnerabilities, checked against your stack, so when the next big disclosure drops you know whether it affects you. This week made the case. On Wednesday, PHP2Shell, LiteLLM and Railway all disclosed security issues. PHP2Shell had sat in PHP's code for over a decade until one researcher using frontier AI turned it into a working exploit in about a week. Cloudflare saw thousands of exploit attempts in the 10 hours before disclosure and millions since. Starting today, anyone can sign up. Try it free for 14 days:

Big news: Enclave is now open to everyone, and today we're launching Threat Feed. Enclave is an autonomous security team for AI-native companies: a fleet of security agents that test your code, cloud, and infrastructure the way an attacker would. We built it on a simple belief. Attackers already use swarms of cheap AI agents to probe for weaknesses around the clock, so defenders need agents of their own to keep up. A small team without a security function should be able to defend like a large one. Threat Feed is the newest piece: a live feed of new vulnerabilities, checked against your stack, so when the next big disclosure drops you know whether it affects you. This week made the case. On Wednesday, PHP2Shell, LiteLLM and Railway all disclosed security issues. PHP2Shell had sat in PHP's code for over a decade until one researcher using frontier AI turned it into a working exploit in about a week. Cloudflare saw thousands of exploit attempts in the 10 hours before disclosure and millions since. Starting today, anyone can sign up. Try it free for 14 days:

Enclave

809,939 次观看 • 19 天前

THIS IS THE MOST COMPLETE CLAUDE CODE SETUP I'VE EVER SEEN someone open-sourced a full agent harness for Claude Code 38 agents. 156 skills. 72 commands. all pre-configured the kind of setup you'd spend weeks building yourself what's inside: → planner - feature implementation planning → architect - system design decisions → tdd-guide - test-driven development workflow → code-reviewer - quality and security review → security-reviewer - vulnerability analysis → build-error-resolver - fixes broken builds → refactor-cleaner - dead code cleanup → doc-updater - keeps docs in sync → chief-of-staff - communication triage → + 29 more agents 156 skills covering token optimization, memory persistence, continuous learning, verification loops, parallelization, subagent orchestration it ships with AgentShield baked in a security auditor that runs vulnerability checks on every agent action before execution works on Claude Code, Cursor, OpenCode, and Codex CLI one repo, one install, configured everywhere one warning: loading 38 agents and 156 skills into your context at once will burn your usage limits in minutes pick the 3-4 you actually need and load only those free. open-source. MIT licensed like + bookmark - you'll need this

THIS IS THE MOST COMPLETE CLAUDE CODE SETUP I'VE EVER SEEN someone open-sourced a full agent harness for Claude Code 38 agents. 156 skills. 72 commands. all pre-configured the kind of setup you'd spend weeks building yourself what's inside: → planner - feature implementation planning → architect - system design decisions → tdd-guide - test-driven development workflow → code-reviewer - quality and security review → security-reviewer - vulnerability analysis → build-error-resolver - fixes broken builds → refactor-cleaner - dead code cleanup → doc-updater - keeps docs in sync → chief-of-staff - communication triage → + 29 more agents 156 skills covering token optimization, memory persistence, continuous learning, verification loops, parallelization, subagent orchestration it ships with AgentShield baked in a security auditor that runs vulnerability checks on every agent action before execution works on Claude Code, Cursor, OpenCode, and Codex CLI one repo, one install, configured everywhere one warning: loading 38 agents and 156 skills into your context at once will burn your usage limits in minutes pick the 3-4 you actually need and load only those free. open-source. MIT licensed like + bookmark - you'll need this

self.dll

19,962 次观看 • 7 个月前

Run AI Agents locally in your terminal using Llama 3.2! gptme: Run Code, edit files, browse the web, and add context with RAG - all from your terminal. 100% Open Source.

Run AI Agents locally in your terminal using Llama 3.2! gptme: Run Code, edit files, browse the web, and add context with RAG - all from your terminal. 100% Open Source.

Sumanth

78,860 次观看 • 1 年前

Why settle for one Claude Code when you can run ten in parallel? We built Claude Squad — a manager for Claude Code & Aider tasks: • Supervise multiple agents in one place • Isolated git workspaces Free + open-source:

Why settle for one Claude Code when you can run ten in parallel? We built Claude Squad — a manager for Claude Code & Aider tasks: • Supervise multiple agents in one place • Isolated git workspaces Free + open-source:

mufeez

120,932 次观看 • 1 年前

Let your Grok Bot / Muse talk to your Claude Code / Codex or any other agents Introducing Reason Network, Free, peer to peer and Open-Source Engine Loop in your teammates too so no live agents work collides when coding. Try it for free: one click install and setup!

Let your Grok Bot / Muse talk to your Claude Code / Codex or any other agents Introducing Reason Network, Free, peer to peer and Open-Source Engine Loop in your teammates too so no live agents work collides when coding. Try it for free: one click install and setup!

Reason Machines (YC F26)

620,670 次观看 • 27 天前

miami shapers! we made it super easy to claim your bubble(s) ↓ → scan your qr code or navigate to from your browser → click “claim” → enter your email address (or connect your wallet if you have one) → enter the otp (one time password) sent to your email for security → once signed in enter your claim code and accept terms → click claim → enjoy your bubble(s)! 🫧

miami shapers! we made it super easy to claim your bubble(s) ↓ → scan your qr code or navigate to from your browser → click “claim” → enter your email address (or connect your wallet if you have one) → enter the otp (one time password) sent to your email for security → once signed in enter your claim code and accept terms → click claim → enjoy your bubble(s)! 🫧

Shape

26,704 次观看 • 11 个月前

Your AI agents can now learn multiple skills at once. /learn batch One command. All skills. Parallel. Watch Claude Code learn your entire stack at once. Powered by Hyperbrowser, Setup Guide ↓

Your AI agents can now learn multiple skills at once. /learn batch One command. All skills. Parallel. Watch Claude Code learn your entire stack at once. Powered by Hyperbrowser, Setup Guide ↓

Hyperbrowser

25,518 次观看 • 8 个月前

hey builders! showcasing your code & CLI w HyperFrames got 10x easier We open sourced accurate, pre-built UI components A Mac terminal. A VS Code window. Free. One command to install $ npx hyperframes add code Swap in your own code or commands and go

hey builders! showcasing your code & CLI w HyperFrames got 10x easier We open sourced accurate, pre-built UI components A Mac terminal. A VS Code window. Free. One command to install $ npx hyperframes add code Swap in your own code or commands and go

HeyGen

256,226 次观看 • 5 个月前

Your ad spend lives in 5 different dashboards. Meta, Google, TikTok, LinkedIn, X, all with their own metrics, all in separate tabs. So we built one dashboard that shows every ad, every platform, one screen. And we open-sourced it. Link below 👇

Your ad spend lives in 5 different dashboards. Meta, Google, TikTok, LinkedIn, X, all with their own metrics, all in separate tabs. So we built one dashboard that shows every ad, every platform, one screen. And we open-sourced it. Link below 👇

Miki Palet

18,469 次观看 • 3 个月前

Announcing: Railway Sandboxes Spin up thousands of VMs right next to your infra on Railway Run, checkpoint, and fork and let your agents (and code) run

Announcing: Railway Sandboxes Spin up thousands of VMs right next to your infra on Railway Run, checkpoint, and fork and let your agents (and code) run

Railway

76,073 次观看 • 1 个月前

We open sourced Claude Artifacts for your own apps. Ask your agent to visualize algorithms, create 3D animations, render charts, or generate interactive diagrams. PLUS it runs the generated code securely w/ sandbox iframe. It's additive to your app, so you can drop it in with one toggle. ➡️

We open sourced Claude Artifacts for your own apps. Ask your agent to visualize algorithms, create 3D animations, render charts, or generate interactive diagrams. PLUS it runs the generated code securely w/ sandbox iframe. It's additive to your app, so you can drop it in with one toggle. ➡️

Atai Barkai

87,741 次观看 • 6 个月前

You've been asking for it...so here it is! One-click agent deploy is now available at Launch your SolClaw with the click of a button. We handle everything else. Deploy your agents today: AI on Solana couldn't be easier.

You've been asking for it...so here it is! One-click agent deploy is now available at Launch your SolClaw with the click of a button. We handle everything else. Deploy your agents today: AI on Solana couldn't be easier.

SolClaw

61,283 次观看 • 8 个月前

Give your AI one link. Get a game you control with your hands. Open sourced kit in replies. Here are 15 games I made with it, what will you build? 👇 - no controller, just your webcam - made with Claude Code, fal, Three.js, Tripo, and a dream

Give your AI one link. Get a game you control with your hands. Open sourced kit in replies. Here are 15 games I made with it, what will you build? 👇 - no controller, just your webcam - made with Claude Code, fal, Three.js, Tripo, and a dream

Meticulai

88,727 次观看 • 9 天前

.Veria Labs' AI agents continuously pentest your code. Companies ship code daily but test for security once a year. Traditional pentests take weeks and cost $30K+. Veria's agents run 24/7 and find vulnerabilities human pentesters miss. Congrats on the launch, jayden, SuperBeetleGamer, and Joana!

.Veria Labs' AI agents continuously pentest your code. Companies ship code daily but test for security once a year. Traditional pentests take weeks and cost $30K+. Veria's agents run 24/7 and find vulnerabilities human pentesters miss. Congrats on the launch, jayden, SuperBeetleGamer, and Joana!

Y Combinator

14,427 次观看 • 1 年前

🧵 Making Proactive Agents with Code Generation Last week we shared about how you can use code generation to compose tools. But code generation can also give your agents new capabilities- like proactively acting on your behalf.

🧵 Making Proactive Agents with Code Generation Last week we shared about how you can use code generation to compose tools. But code generation can also give your agents new capabilities- like proactively acting on your behalf.

Thariq

35,797 次观看 • 1 年前

Everyone talks about loops - but no one shows you a real one SToneX and I spent a month running loops to automate most of SuperDesign.Dev - many many of them. Some worked, some didn't Recorded a 14-min walkthrough on key learnings with the real examples we run 👇 ------- Open-sourced our internal tool to manage loops: + Skill for setup verifier:

Everyone talks about loops - but no one shows you a real one SToneX and I spent a month running loops to automate most of SuperDesign.Dev - many many of them. Some worked, some didn't Recorded a 14-min walkthrough on key learnings with the real examples we run 👇 ------- Open-sourced our internal tool to manage loops: + Skill for setup verifier:

Jason Zhou

28,711 次观看 • 4 个月前

prompting tip: How to write hybrid english & code prompts while building custom GPTs -Turn on code interpreter -"write code to ..." -Regenerate a few times until you get one you like -Copy paste it back into your prompt -tweak it to improve Now your ai can write consistent code Plus, you can add & combine with all sorts of english rules on top. Essentially adding english code logic "If the user asks for ..., then run this code" "If the user needs help with ..., use this code snippet and ask the user for all required information" Guess what thats a working if statement in english! if userAsksFor { // run this code } Prompts are code! English is a coding language Prompt-gramming is abstract coding

prompting tip: How to write hybrid english & code prompts while building custom GPTs -Turn on code interpreter -"write code to ..." -Regenerate a few times until you get one you like -Copy paste it back into your prompt -tweak it to improve Now your ai can write consistent code Plus, you can add & combine with all sorts of english rules on top. Essentially adding english code logic "If the user asks for ..., then run this code" "If the user needs help with ..., use this code snippet and ask the user for all required information" Guess what thats a working if statement in english! if userAsksFor { // run this code } Prompts are code! English is a coding language Prompt-gramming is abstract coding

Nick Dobos

117,072 次观看 • 2 年前