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。

Introducing: (built on Cloudflare Containers + Bun) Deploy a Cloudflare Worker or a static website directly in the browser! ⛅️⚡️ * no login needed * drag-and-drop template from Gitlip, GitHub, etc * global deployment in seconds * TS, JS and PY workers * arbitrary NPM dependencies * wrangler config... show more

Natalie Marleny

7,483 subscribers

15,442 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

11 条评论

Natalie Marleny 的头像

Natalie Marleny1 年前

All features on Gitlip are multiplayer including: Git repositories, collaborative editors and (now also) global deployments. We’ll introduce a few other ways to get started with Gitlip in the coming days 📆💫 We’ll also enable configuring other bindings (object storage, AI, etc.) … and one or two other big features!

Natalie Marleny 的头像

Natalie Marleny1 年前

Our JS+TS build pipeline is powered by the recently released Cloudflare Containers and by the very speedy Bun.js. We’re building an agentic coding platform entirely on Cloudflare. Stay tuned for more! 🌷💫

Mobile Scanner 的头像

Mobile Scanner1 年前

Scan any documents, convert images into text, PDF files, etc. 👍

Jonas Templestein 的头像

Jonas Templestein1 年前

@Cloudflare @bunjavascript @GitlipDotCom So cool!

Natalie Marleny 的头像

Natalie Marleny1 年前

@Cloudflare @bunjavascript @GitlipDotCom Thank you 😌

toki 🇨🇦 的头像

toki 🇨🇦1 年前

@Cloudflare @bunjavascript @GitlipDotCom cool stuff

Natalie Marleny 的头像

Natalie Marleny1 年前

@Cloudflare @bunjavascript @GitlipDotCom Appreciate it! 🚀

Indy Singh 的头像

Indy Singh1 年前

@Cloudflare @bunjavascript @GitlipDotCom Excellent idea for video series. Backdrop gets more and more British. Sweltering in the garden ✅ In a noisy pub On the tube Hyde park British museum You get the idea.

Natalie Marleny 的头像

Natalie Marleny1 年前

@Cloudflare @bunjavascript @GitlipDotCom 😂 vibe code from the pub, shipping from the Lizzie line, I love it 🇬🇧🚀

Abhishek 的头像

Abhishek1 年前

@Samhanknr @Cloudflare @bunjavascript @GitlipDotCom This is so cool 👌

Natalie Marleny 的头像

Natalie Marleny1 年前

@Samhanknr @Cloudflare @bunjavascript @GitlipDotCom Thank you! ☃️❄️

相关视频

Introducing the Knowledge Agent Template Vercel dropped the Chat SDK so we built a full template on top of it that you can deploy in one click. Here's what's inside: • Add your sources: GitHub repos, YouTube, etc. directly from the UI • File-based agent using grep/find/cat • Powered by Vercel Workflow + Sandbox • Multi-platform: web chat, GitHub bot, Discord bot, and more • Comes with skills to edit your project, add sources, create agents Deploy, add a source, ask questions. Your knowledge base is live and always in sync. This is just scratching the surface. There's way more packed in this template, and I'll be breaking down the features all week. Links in the below 👇

Introducing the Knowledge Agent Template Vercel dropped the Chat SDK so we built a full template on top of it that you can deploy in one click. Here's what's inside: • Add your sources: GitHub repos, YouTube, etc. directly from the UI • File-based agent using grep/find/cat • Powered by Vercel Workflow + Sandbox • Multi-platform: web chat, GitHub bot, Discord bot, and more • Comes with skills to edit your project, add sources, create agents Deploy, add a source, ask questions. Your knowledge base is live and always in sync. This is just scratching the surface. There's way more packed in this template, and I'll be breaking down the features all week. Links in the below 👇

Hugo

54,769 次观看 • 6 个月前

new portfolio — 1,600+ images and videos of art I've made across various mediums over the last 4 years: • are.na-style grid with video & gallery image previews on hover, adjustable columns, shareable post links • hdr image + video support in the fullscreen viewer • tag filtering across medium, style, subject, technology, year & media type (stack tags to drill down further) • keyboard shortcuts - ‘c’ for toggling visibility of post captions, ’t’ for toggling sidebar visibility under the hood, I built a custom CMS to manage and view all media: • vanilla js, html, css - no framework or dependencies • static site + cloudflare workers (d1 database, r2 storage) • media processing happens in-browser at upload, keeping the backend small (~$5/mo for everything) • frontend admin portal for managing and publishing media hope you enjoy checking it out. the cube in the header spins if you drag or click it!

new portfolio — 1,600+ images and videos of art I've made across various mediums over the last 4 years: • are.na-style grid with video & gallery image previews on hover, adjustable columns, shareable post links • hdr image + video support in the fullscreen viewer • tag filtering across medium, style, subject, technology, year & media type (stack tags to drill down further) • keyboard shortcuts - ‘c’ for toggling visibility of post captions, ’t’ for toggling sidebar visibility under the hood, I built a custom CMS to manage and view all media: • vanilla js, html, css - no framework or dependencies • static site + cloudflare workers (d1 database, r2 storage) • media processing happens in-browser at upload, keeping the backend small (~$5/mo for everything) • frontend admin portal for managing and publishing media hope you enjoy checking it out. the cube in the header spins if you drag or click it!

Adam Fuhrer

80,618 次观看 • 1 个月前

I built a self-hosted Sentry clone that runs entirely on Cloudflare Workers, and I think it showcases one of the most underrated features in the Cloudflare ecosystem: Service Bindings. Let me explain why this matters. When you have multiple Cloudflare Workers (an API, a webhook handler, a cron job), they all need common things: error tracking, authentication, rate limiting, metrics. The typical solution? External HTTP calls to third-party services. That means: - 50-200ms latency per call - Egress fees - Your data leaving your infrastructure - Another vendor to manage Service bindings let Workers call each other directly inside Cloudflare's network. No HTTP. No internet. Just internal RPC with <5ms latency. With Workers Sentinel, any Worker in my account can just point Sentry-SDK into the Service binding, and have all errors flow into one centralized dashboard, stored in Durable Objects with SQLite. No external calls. No added latency. Service bindings aren't just for error tracking. You can centralize: 🔐 Authentication — One Worker that validates tokens for all your services 📊 Metrics — Centralized collection without external observability costs 🚦 Rate Limiting — Shared counters that actually work across Workers 🚩 Feature Flags — Instant propagation, no deployment needed Think of it as building your own internal microservices mesh, but at the edge, with zero network overhead. Workers Sentinel uses two Durable Objects: - AuthState (singleton) — users, sessions, projects - ProjectState (per-project) — issues, events, stats Events are fingerprinted and grouped intelligently. The dashboard is a Vue.js app served from the same Worker. I could say i built this to learn Durable Objects or that I needed error tracking for side projects, but honestly I just need a way to show my wife why I'm sending $200/month to some guy named Claudio who apparently helps me write code. The whole thing is open source. Deploy it to your Cloudflare account, point your Sentry SDKs at it, and you're done. But more importantly: take a closer look at service bindings. They're the glue that turns a collection of Workers into an actual platform. Most Cloudflare customers I talk to aren't using them, and they're missing out. To the Sentry team: I love your work. Genuinely. Sentry is battle-tested, has incredible features, and is what you should use for anything that matters. This project is a toy. A learning exercise. A weekend hack that got slightly out of hand. Please do not trust your production errors to this dummy clone. If your startup goes down at 3 AM because Workers Sentinel missed an edge case, that's on you. I warned you. Use the real thing. But if you want to learn about Durable Objects, service bindings, and how error tracking works under the hood? Clone away. Your Workers shouldn't be islands. Connect them.

I built a self-hosted Sentry clone that runs entirely on Cloudflare Workers, and I think it showcases one of the most underrated features in the Cloudflare ecosystem: Service Bindings. Let me explain why this matters. When you have multiple Cloudflare Workers (an API, a webhook handler, a cron job), they all need common things: error tracking, authentication, rate limiting, metrics. The typical solution? External HTTP calls to third-party services. That means: - 50-200ms latency per call - Egress fees - Your data leaving your infrastructure - Another vendor to manage Service bindings let Workers call each other directly inside Cloudflare's network. No HTTP. No internet. Just internal RPC with <5ms latency. With Workers Sentinel, any Worker in my account can just point Sentry-SDK into the Service binding, and have all errors flow into one centralized dashboard, stored in Durable Objects with SQLite. No external calls. No added latency. Service bindings aren't just for error tracking. You can centralize: 🔐 Authentication — One Worker that validates tokens for all your services 📊 Metrics — Centralized collection without external observability costs 🚦 Rate Limiting — Shared counters that actually work across Workers 🚩 Feature Flags — Instant propagation, no deployment needed Think of it as building your own internal microservices mesh, but at the edge, with zero network overhead. Workers Sentinel uses two Durable Objects: - AuthState (singleton) — users, sessions, projects - ProjectState (per-project) — issues, events, stats Events are fingerprinted and grouped intelligently. The dashboard is a Vue.js app served from the same Worker. I could say i built this to learn Durable Objects or that I needed error tracking for side projects, but honestly I just need a way to show my wife why I'm sending $200/month to some guy named Claudio who apparently helps me write code. The whole thing is open source. Deploy it to your Cloudflare account, point your Sentry SDKs at it, and you're done. But more importantly: take a closer look at service bindings. They're the glue that turns a collection of Workers into an actual platform. Most Cloudflare customers I talk to aren't using them, and they're missing out. To the Sentry team: I love your work. Genuinely. Sentry is battle-tested, has incredible features, and is what you should use for anything that matters. This project is a toy. A learning exercise. A weekend hack that got slightly out of hand. Please do not trust your production errors to this dummy clone. If your startup goes down at 3 AM because Workers Sentinel missed an edge case, that's on you. I warned you. Use the real thing. But if you want to learn about Durable Objects, service bindings, and how error tracking works under the hood? Clone away. Your Workers shouldn't be islands. Connect them.

Gabriel Massadas

28,840 次观看 • 7 个月前

introducing AlphaClaw Apex 🐺 a native Mac app for managing multiple OpenClaw VPS instances from one dashboard. some of you are already setting up OpenClaw for clients as a service. Apex is built for you. deploy to Hetzner VPS in one click. monitor all your instances. manage configs, updates, spend, and health from a single UI. no SSH needed. everything you know from AlphaClaw, now across a fleet: 📅 Google Workspace OAuth & pubsub wizard ⏱️ Cron calendar view and cost-saving insights 🖥️ Remote node setup wizard 🔄 Auto-backup to GitHub 📊 Token usage & cost analytics built in 🧱 Prompt hardening reduces agent drift 🩺 Drift Doctor analyzes your prompts and workspace for drift 💬 Telegram multi-topic workspace setup wizard 📂 Full file browser, editor, and terminal no SSH needed 🐕 Per-instance watchdog and crash recovery 🛠️ Manage env vars from the UI 🔑 Manage model keys & OAuth visually 🪝 Webhook creator & inspector with replay & debug ⬆️ One-click updates, no redeploy needed 📦 Import existing setup from GitHub if you're thinking about offering managed OpenClaw as a service, this is the ops layer you've been missing.

introducing AlphaClaw Apex 🐺 a native Mac app for managing multiple OpenClaw VPS instances from one dashboard. some of you are already setting up OpenClaw for clients as a service. Apex is built for you. deploy to Hetzner VPS in one click. monitor all your instances. manage configs, updates, spend, and health from a single UI. no SSH needed. everything you know from AlphaClaw, now across a fleet: 📅 Google Workspace OAuth & pubsub wizard ⏱️ Cron calendar view and cost-saving insights 🖥️ Remote node setup wizard 🔄 Auto-backup to GitHub 📊 Token usage & cost analytics built in 🧱 Prompt hardening reduces agent drift 🩺 Drift Doctor analyzes your prompts and workspace for drift 💬 Telegram multi-topic workspace setup wizard 📂 Full file browser, editor, and terminal no SSH needed 🐕 Per-instance watchdog and crash recovery 🛠️ Manage env vars from the UI 🔑 Manage model keys & OAuth visually 🪝 Webhook creator & inspector with replay & debug ⬆️ One-click updates, no redeploy needed 📦 Import existing setup from GitHub if you're thinking about offering managed OpenClaw as a service, this is the ops layer you've been missing.

Chrys Bader

67,550 次观看 • 5 个月前

DFIR analysts who use macOS as their daily driver deserve free and native forensic tooling. So I built one. 🍎 Introducing 𝗜𝗥𝗙𝗹𝗼𝘄 𝗧𝗶𝗺𝗲𝗹𝗶𝗻𝗲 — a timeline analysis app built from the ground up for Mac-based DFIR folks, forensic investigators, or SOC analysts. Built in appreciation of, and inspired by, Eric Zimmerman’s Timeline Explorer. Every feature in this tool was shaped by real IR casework. Handling massive timelines, parsing artifacts here and there, and pivoting across logs during active investigations. I built IRFlow Timeline to be the native macOS timeline analyzer that actually keeps up with a live case. Every button and view is intentional; if it’s in the app, it’s because I needed it mid-case and realized the standard tools fell short. No dependencies. Zero setup. Just drag, drop, and analyze. #dfir #incidentresponse #timeline #macos #threathunitng #digitalforensics

DFIR analysts who use macOS as their daily driver deserve free and native forensic tooling. So I built one. 🍎 Introducing 𝗜𝗥𝗙𝗹𝗼𝘄 𝗧𝗶𝗺𝗲𝗹𝗶𝗻𝗲 — a timeline analysis app built from the ground up for Mac-based DFIR folks, forensic investigators, or SOC analysts. Built in appreciation of, and inspired by, Eric Zimmerman’s Timeline Explorer. Every feature in this tool was shaped by real IR casework. Handling massive timelines, parsing artifacts here and there, and pivoting across logs during active investigations. I built IRFlow Timeline to be the native macOS timeline analyzer that actually keeps up with a live case. Every button and view is intentional; if it’s in the app, it’s because I needed it mid-case and realized the standard tools fell short. No dependencies. Zero setup. Just drag, drop, and analyze. #dfir #incidentresponse #timeline #macos #threathunitng #digitalforensics

Renzon

41,919 次观看 • 6 个月前

The first universal 3D robot viewer for the browser… load URDF, MJCF, or USD in seconds. No installs. No setup. Developer Victor Oldensand has built Mechaverse, a universal 3D robotics viewer that works on desktop and even mobile (if your phone is strong enough). No installs. No setup. Just drag and drop your robot model. Mechaverse merges and improves the work of several open-source projects, including: ✅ Mujoco_wasm (MuJoCo in the browser) ✅ USD-viewer (OpenUSD) ✅ URDF-loaders … into one clean, cross-platform tool. 💻 Try it here: Built in just 4 days, it supports URDF, MJCF, and OpenUSD formats via Three.js, with rendering powered by WebAssembly. Perfect for quickly inspecting robot models or scenes without heavyweight desktop software.

The first universal 3D robot viewer for the browser… load URDF, MJCF, or USD in seconds. No installs. No setup. Developer Victor Oldensand has built Mechaverse, a universal 3D robotics viewer that works on desktop and even mobile (if your phone is strong enough). No installs. No setup. Just drag and drop your robot model. Mechaverse merges and improves the work of several open-source projects, including: ✅ Mujoco_wasm (MuJoCo in the browser) ✅ USD-viewer (OpenUSD) ✅ URDF-loaders … into one clean, cross-platform tool. 💻 Try it here: Built in just 4 days, it supports URDF, MJCF, and OpenUSD formats via Three.js, with rendering powered by WebAssembly. Perfect for quickly inspecting robot models or scenes without heavyweight desktop software.

Ilir Aliu

40,101 次观看 • 1 年前

businesss owners spend weeks and $$$ launching their website so i built a solution to help them go live in pick your business category, aesthetic, and brand name > generate hero images, brand palettes and product shots in one-click deploy Netlify and go live immediately > your landing page comes with custom copy; edit in-line and re-deploy if needed > product menus are already calibrated to your business type > all requests runs through your Visa card in real time; no billing inputs or invoices this is command line commerce for merchants, by merchants your first site is on me comment "premiere" below or DM to get access

Mashiat

11,330 次观看 • 4 个月前

I built a mobile app to check Paddle revenue (because they don't have one): 👉 - Use your Paddle API key (read-only and scoped) - Live data with beautiful and useful graphs built with native Swift UI. - Multi-account supported, unified revenue metrics. - Data stay on device, no server (api requests are sent directly from your phone) - Home widgets - I made it free to download on App Store (once it's approved) - Buy the source code for $19 and customize it however you want (save 5hrs of prompting if you try to do it yourself). Some interesting facts about this side project: - I vibe coded with 100% claude code remotely on my Mac Mini (with my AI assistant setup) in less than 24 hours. - I have read 0 line of code in this project and never opened Xcode myself. - My AI assistant designed the app with GPT Image 2, built the app with Swift UI, test it on simulator (via screenshots), send the test build to TestFlight for me to test, and invited me to the app store connect account so I can test on my phone, then the AI submitted the app to App Store and currently waiting for approval. - For the website, I ask it to come up with a domain name, I bought it via manually and give it access via Cloudflare API, the AI design and create a static website with GitHub, test it with lighthouse CLI, deploy via GitHub pages, config the domain DNS, deploy the website. - Then I sign up an account with Polar payment, create an API key and ask the AI to setup a store, add payment, link with the account, and add the payment to the website. The entire process happened in the last 24 hours with me only talking to the AI via Telegram. This is such a fun side project not only to create an app that I wish exists, but also to push the limit of what I can use AI for, and so far I'm very impressed. I'll create so much more apps! It feels like I have unlocked a super power.

I built a mobile app to check Paddle revenue (because they don't have one): 👉 - Use your Paddle API key (read-only and scoped) - Live data with beautiful and useful graphs built with native Swift UI. - Multi-account supported, unified revenue metrics. - Data stay on device, no server (api requests are sent directly from your phone) - Home widgets - I made it free to download on App Store (once it's approved) - Buy the source code for $19 and customize it however you want (save 5hrs of prompting if you try to do it yourself). Some interesting facts about this side project: - I vibe coded with 100% claude code remotely on my Mac Mini (with my AI assistant setup) in less than 24 hours. - I have read 0 line of code in this project and never opened Xcode myself. - My AI assistant designed the app with GPT Image 2, built the app with Swift UI, test it on simulator (via screenshots), send the test build to TestFlight for me to test, and invited me to the app store connect account so I can test on my phone, then the AI submitted the app to App Store and currently waiting for approval. - For the website, I ask it to come up with a domain name, I bought it via manually and give it access via Cloudflare API, the AI design and create a static website with GitHub, test it with lighthouse CLI, deploy via GitHub pages, config the domain DNS, deploy the website. - Then I sign up an account with Polar payment, create an API key and ask the AI to setup a store, add payment, link with the account, and add the payment to the website. The entire process happened in the last 24 hours with me only talking to the AI via Telegram. This is such a fun side project not only to create an app that I wish exists, but also to push the limit of what I can use AI for, and so far I'm very impressed. I'll create so much more apps! It feels like I have unlocked a super power.

Tony Dinh

43,922 次观看 • 3 个月前

SOME GUY BUILT A 24/7 ONLINE RAVE IN YOUR BROWSER AND IT IS COMPLETELY FREE TO ATTEND it's called Hallucinate. you click one link, your browser loads a 3D field at night, and suddenly you are standing in a crowd of hundreds of low-poly strangers dancing under a moon to a youtube video playing on a giant screen. there is no login. there is no wallet. there is no signup. you are just at the rave. the rave has its own keyboard. > 7 and 8 cycle your hair color > 9 and 0 cycle your skin tone > U and I cycle your hair style > L and ; cycle your dance moves > V is the wave emote > B is the bounce emote > SPACE bar is literally labeled "speak" every other person in the room is a real human pressing the same keys, in real time. nobody ever stops dancing because the creator wrote on hacker news: "everybody dancing forever is crucial for the feeling. you don't stop dancing in a rave." the dev who made it goes by the handle stagas. he says the entire thing was "vibe coded in its entirety" by an LLM. the commit messages on the repo are three words long: "cool." "jump jump." "perf." he has about 500 other repos on his github account. the post went up on Show HN two days ago. it is currently sitting at 435 points and 193 comments and the top discussion in the thread is people arguing whether magic numbers in shaders.ts disqualify you from getting a job. we built the global internet so that two strangers across the planet could fall in love or trade stocks or topple regimes. and the very best thing happening on it right now is a thousand cubes dancing forever under a fake moon. the internet is healing.

SOME GUY BUILT A 24/7 ONLINE RAVE IN YOUR BROWSER AND IT IS COMPLETELY FREE TO ATTEND it's called Hallucinate. you click one link, your browser loads a 3D field at night, and suddenly you are standing in a crowd of hundreds of low-poly strangers dancing under a moon to a youtube video playing on a giant screen. there is no login. there is no wallet. there is no signup. you are just at the rave. the rave has its own keyboard. > 7 and 8 cycle your hair color > 9 and 0 cycle your skin tone > U and I cycle your hair style > L and ; cycle your dance moves > V is the wave emote > B is the bounce emote > SPACE bar is literally labeled "speak" every other person in the room is a real human pressing the same keys, in real time. nobody ever stops dancing because the creator wrote on hacker news: "everybody dancing forever is crucial for the feeling. you don't stop dancing in a rave." the dev who made it goes by the handle stagas. he says the entire thing was "vibe coded in its entirety" by an LLM. the commit messages on the repo are three words long: "cool." "jump jump." "perf." he has about 500 other repos on his github account. the post went up on Show HN two days ago. it is currently sitting at 435 points and 193 comments and the top discussion in the thread is people arguing whether magic numbers in shaders.ts disqualify you from getting a job. we built the global internet so that two strangers across the planet could fall in love or trade stocks or topple regimes. and the very best thing happening on it right now is a thousand cubes dancing forever under a fake moon. the internet is healing.

Nav Toor

249,078 次观看 • 3 个月前

I was laid off so I rebuilt their product but better (in 2 weeks from scratch) Open Canvas - a multiplayer site builder with an agent at the cursor. Most website builders ask you to fill in a template.I built one that lets you design - on a free-form canvas, with an AI agent at your cursor, where your whole team co-edits live and visitors see your publish update without refreshing. What makes it different: • Drag 14 design primitives anywhere — not into fixed slots • AI agent edits in plain English, you preview before it lands • Real-time co-editing (Yjs CRDT, Figma-style cursors) • Publish → every open visitor tab updates in <100ms Under the hood: one Cloudflare Worker, serverless Postgres, a first-class CMS, version history, a blocking accessibility audit, AI image gen, custom domains — all shipping as pure HTML, zero client-framework weight. It's MIT-licensed and built in the open

I was laid off so I rebuilt their product but better (in 2 weeks from scratch) Open Canvas - a multiplayer site builder with an agent at the cursor. Most website builders ask you to fill in a template.I built one that lets you design - on a free-form canvas, with an AI agent at your cursor, where your whole team co-edits live and visitors see your publish update without refreshing. What makes it different: • Drag 14 design primitives anywhere — not into fixed slots • AI agent edits in plain English, you preview before it lands • Real-time co-editing (Yjs CRDT, Figma-style cursors) • Publish → every open visitor tab updates in <100ms Under the hood: one Cloudflare Worker, serverless Postgres, a first-class CMS, version history, a blocking accessibility audit, AI image gen, custom domains — all shipping as pure HTML, zero client-framework weight. It's MIT-licensed and built in the open

Aayushman Singh

195,651 次观看 • 2 个月前

Your Google Maps listing gets views… but you don’t own the traffic. Build a full website or app from a single prompt with Autocoder. Autocoder generates frontend, backend, and database instantly — giving you a ready-to-deploy product in minutes. Features: Prompt → Full App → Deployment ☑️ Fully exportable frontend + backend code ☑️ Export complete source code ☑️ Instant custom domain launch ☑️ Templates for cafes, portfolios, e-commerce & local businesses ☑️ Built-in admin dashboard (manage content, users, bookings) 📈 Turn Google Maps traffic into your own website visitors with Autocoder. ⚡ What you get: • Ready-to-use backend + database (no developer needed) • Built-in admin dashboard to manage content, users, and bookings • Scalable workflow for building sites for multiple local businesses • Full source code export for Pro users to modify or extend AutoCoder.cc #Autocoder #AIWeb #NoCodeAI #WebGenerator

Your Google Maps listing gets views… but you don’t own the traffic. Build a full website or app from a single prompt with Autocoder. Autocoder generates frontend, backend, and database instantly — giving you a ready-to-deploy product in minutes. Features: Prompt → Full App → Deployment ☑️ Fully exportable frontend + backend code ☑️ Export complete source code ☑️ Instant custom domain launch ☑️ Templates for cafes, portfolios, e-commerce & local businesses ☑️ Built-in admin dashboard (manage content, users, bookings) 📈 Turn Google Maps traffic into your own website visitors with Autocoder. ⚡ What you get: • Ready-to-use backend + database (no developer needed) • Built-in admin dashboard to manage content, users, and bookings • Scalable workflow for building sites for multiple local businesses • Full source code export for Pro users to modify or extend AutoCoder.cc #Autocoder #AIWeb #NoCodeAI #WebGenerator

Ai With Piyas

20,612 次观看 • 5 个月前

Introducing 🌸 Kanna – a web ui for Claude Code + Codex running right in your browser (and my first open source project!) It's sort of like if Claude Code & Codex had a baby with a much better ui/ux 💅 Here's what makes Kanna special: 🔀 One-click switch between Claude Code / Codex 🌐 Runs in your browser on localhost - no app switching 🧩 Embedded split terminals, persisted between chats with a beautiful horizontal scrolling UX 📁 Full project file browser built in, embedded editor coming soon too. Coming soon: 🔒 End-to-end encryption + remote access via reverse proxy 🌿 Git integration, diffs, PRs 🧱 Plugins I wanted to replace switching between cursor, the github app, browser & (most recently) the codex app. The browser is hardest to recreate yet also the most flexible so it makes sense to build in the browser itself. Install in 5 seconds: bun install -g kanna-code then just type: kanna Kanna is purely a ui/ux layer. It uses your existing CLIs, is 100% compliant & no data ever leaves your machine. If running claude or codex in your terminal works, kanna works too. Kanna natively supports every tool call, model, reasoning effort, fast mode, plan mode, compaction, user questions, web searching, skills, agents, mcps, everything. There are a few libraries that do this but none that I found as comprehensive. All feedback welcome!

Introducing 🌸 Kanna – a web ui for Claude Code + Codex running right in your browser (and my first open source project!) It's sort of like if Claude Code & Codex had a baby with a much better ui/ux 💅 Here's what makes Kanna special: 🔀 One-click switch between Claude Code / Codex 🌐 Runs in your browser on localhost - no app switching 🧩 Embedded split terminals, persisted between chats with a beautiful horizontal scrolling UX 📁 Full project file browser built in, embedded editor coming soon too. Coming soon: 🔒 End-to-end encryption + remote access via reverse proxy 🌿 Git integration, diffs, PRs 🧱 Plugins I wanted to replace switching between cursor, the github app, browser & (most recently) the codex app. The browser is hardest to recreate yet also the most flexible so it makes sense to build in the browser itself. Install in 5 seconds: bun install -g kanna-code then just type: kanna Kanna is purely a ui/ux layer. It uses your existing CLIs, is 100% compliant & no data ever leaves your machine. If running claude or codex in your terminal works, kanna works too. Kanna natively supports every tool call, model, reasoning effort, fast mode, plan mode, compaction, user questions, web searching, skills, agents, mcps, everything. There are a few libraries that do this but none that I found as comprehensive. All feedback welcome!

Jake Mor

43,379 次观看 • 5 个月前

THIS GUY REBUILT A CHILDHOOD PS2 GAME AS A FREE BROWSER VERSION WITH CLAUDE CODE he grew up obsessed with downhill domination, the ps2 downhill mountain biking game that never got a sequel so he rebuilt the entire thing from scratch > its a full downhill biking game you play right in your browser, nothing to install > the whole thing is one single html file with no separate image, model, or sound files > everything, the track, the bike, the physics, is generated in code, not loaded from assets > built with fable, opus, vanilla js and three.js over multiple sessions of iterating someone even sent a pull request to add controller support, he merged it, and people helped him squash bugs on the fly a dead ps2 game came back to life as an open source community project this is the best use of this stuff

THIS GUY REBUILT A CHILDHOOD PS2 GAME AS A FREE BROWSER VERSION WITH CLAUDE CODE he grew up obsessed with downhill domination, the ps2 downhill mountain biking game that never got a sequel so he rebuilt the entire thing from scratch > its a full downhill biking game you play right in your browser, nothing to install > the whole thing is one single html file with no separate image, model, or sound files > everything, the track, the bike, the physics, is generated in code, not loaded from assets > built with fable, opus, vanilla js and three.js over multiple sessions of iterating someone even sent a pull request to add controller support, he merged it, and people helped him squash bugs on the fly a dead ps2 game came back to life as an open source community project this is the best use of this stuff

Om Patel

22,230 次观看 • 1 个月前

Introducing FlowMaker 🌊🤖 A fully open-source, low-code way of building custom agent workflows. Build agents via a drag and drop interface, run it directly in the app, and also directly export it into a deeply custom workflow backed by LlamaIndex 🦙.TS. It’s a fantastic visual tool to help you get started with agents but also gives you full customizability to build the deepest, most advanced workflows, since everything is backed by code. There’s a lot of great low-code agent tools already, but this is a fully-open source template that you can use or clone/customize for your own needs. It was a fun project by Laurie Voss and is intended to give users an easy-on ramp onto our powerful agent orchestration tooling. Also integrates with LlamaCloud in case you want to integrate your own knowledge base into your agent. FlowMaker app: FlowMaker Repo: LlamaCloud:

Introducing FlowMaker 🌊🤖 A fully open-source, low-code way of building custom agent workflows. Build agents via a drag and drop interface, run it directly in the app, and also directly export it into a deeply custom workflow backed by LlamaIndex 🦙.TS. It’s a fantastic visual tool to help you get started with agents but also gives you full customizability to build the deepest, most advanced workflows, since everything is backed by code. There’s a lot of great low-code agent tools already, but this is a fully-open source template that you can use or clone/customize for your own needs. It was a fun project by Laurie Voss and is intended to give users an easy-on ramp onto our powerful agent orchestration tooling. Also integrates with LlamaCloud in case you want to integrate your own knowledge base into your agent. FlowMaker app: FlowMaker Repo: LlamaCloud:

Jerry Liu

20,434 次观看 • 1 年前

Introducing KausaCompute. Running AI models privately is expensive and complicated. Traditional cloud providers require credit cards, KYC verification, and complex setup processes. For many developers, especially in emerging markets, accessing GPU compute remains out of reach. KausaCompute changes that. Deploy any Docker container with NVIDIA GPU, pay with USDC from Maze Pocket, no KYC, no credit card, no cloud provider account needed. GPU pricing starts at $0.47/hr with competitive rates across all tiers. KausaCompute lives inside KausaLayer Pocket. Open a pocket, swap SOL to USDC using the built-in swap feature, and start deploying GPU containers right away. Everything stays within one ecosystem. What it actually does: Private LLM endpoints. Deploy Llama 3, Mistral, CodeLlama, or any open-source model as a personal API. No one logs the prompts. No one reads the data. Full control. AI coding assistants that never see external servers. Speech-to-text processing for thousands of audio files in minutes instead of hours. Sentiment analysis across millions of data points. Document summarization at scale. Multi-modal AI that processes images and text together. All running on dedicated NVIDIA GPUs. A6000, T4, L4, L40, A100, H100, and more. Pick the hardware, pick the duration, deploy in one click. The billing is straightforward. USDC is deducted from Maze Pocket before deployment. Pro tip: Maze Pocket supports multiple pockets per wallet. Create a dedicated pocket just for KausaCompute to keep GPU spending separate from other activities like trading or transfers. Clean separation, easy tracking. KausaCompute is not another cloud provider. It is the fastest path from USDC to a running GPU, with zero identity requirements. Live now at

Introducing KausaCompute. Running AI models privately is expensive and complicated. Traditional cloud providers require credit cards, KYC verification, and complex setup processes. For many developers, especially in emerging markets, accessing GPU compute remains out of reach. KausaCompute changes that. Deploy any Docker container with NVIDIA GPU, pay with USDC from Maze Pocket, no KYC, no credit card, no cloud provider account needed. GPU pricing starts at $0.47/hr with competitive rates across all tiers. KausaCompute lives inside KausaLayer Pocket. Open a pocket, swap SOL to USDC using the built-in swap feature, and start deploying GPU containers right away. Everything stays within one ecosystem. What it actually does: Private LLM endpoints. Deploy Llama 3, Mistral, CodeLlama, or any open-source model as a personal API. No one logs the prompts. No one reads the data. Full control. AI coding assistants that never see external servers. Speech-to-text processing for thousands of audio files in minutes instead of hours. Sentiment analysis across millions of data points. Document summarization at scale. Multi-modal AI that processes images and text together. All running on dedicated NVIDIA GPUs. A6000, T4, L4, L40, A100, H100, and more. Pick the hardware, pick the duration, deploy in one click. The billing is straightforward. USDC is deducted from Maze Pocket before deployment. Pro tip: Maze Pocket supports multiple pockets per wallet. Create a dedicated pocket just for KausaCompute to keep GPU spending separate from other activities like trading or transfers. Clean separation, easy tracking. KausaCompute is not another cloud provider. It is the fastest path from USDC to a running GPU, with zero identity requirements. Live now at

KausaLayer

10,914 次观看 • 3 个月前

Over the last five to six months, Morphware has entered a new phase of growth. Our roadmap was clear. New clients onboarded in April. UAE deal in Q3. Infrastructure scaling in Q4. Everything aligned exactly when it needed to. Today, multiple sites are under development. Each location is being prepared with proper wiring, transformer stations, cooling and all required infrastructure. This is not a temporary setup. This is long term capacity being built the right way. There is only one moment to scale correctly. We executed that phase. Now it is time to optimize. Supply chain management becomes critical at this level. Shipping new miners. Moving client equipment. Managing real world assets like transformers, containers and high voltage hardware. All of it needs to run smooth and fast. Our goal is simple. New sites must be plug and play. Clients connect to Morphware Power without friction. No delays. No custom fixes. One standard. One system. Because of our growth in 2025, we made a strategic decision. We will build our own mining and AI containers in Paraguay. No overseas shipping. No waiting times. No order limits. These Morphware containers will be fully integrated, branded and ready for deployment. This lowers base costs, improves margins and gives us full control over delivery speed. For new clients moving to Paraguay, we will offer the option to buy or rent these containers. Plug in. Power on. Start operating. That adds another revenue stream in 2026 and on top of that, it’s creating jobs for the locals. Scaling. Optimizing. Delivering. Morphware. $XMW

Over the last five to six months, Morphware has entered a new phase of growth. Our roadmap was clear. New clients onboarded in April. UAE deal in Q3. Infrastructure scaling in Q4. Everything aligned exactly when it needed to. Today, multiple sites are under development. Each location is being prepared with proper wiring, transformer stations, cooling and all required infrastructure. This is not a temporary setup. This is long term capacity being built the right way. There is only one moment to scale correctly. We executed that phase. Now it is time to optimize. Supply chain management becomes critical at this level. Shipping new miners. Moving client equipment. Managing real world assets like transformers, containers and high voltage hardware. All of it needs to run smooth and fast. Our goal is simple. New sites must be plug and play. Clients connect to Morphware Power without friction. No delays. No custom fixes. One standard. One system. Because of our growth in 2025, we made a strategic decision. We will build our own mining and AI containers in Paraguay. No overseas shipping. No waiting times. No order limits. These Morphware containers will be fully integrated, branded and ready for deployment. This lowers base costs, improves margins and gives us full control over delivery speed. For new clients moving to Paraguay, we will offer the option to buy or rent these containers. Plug in. Power on. Start operating. That adds another revenue stream in 2026 and on top of that, it’s creating jobs for the locals. Scaling. Optimizing. Delivering. Morphware. $XMW

Morphware

30,676 次观看 • 8 个月前

🚨 JAILBREAK ALERT 🚨 OPENAI: PWNED 😎 ATLAS-BROWSER: LIBERATED 🙌 WOW! There's a new AI browser on the block! Has some hefty guardrails in play, but the browser surface area is vast 🌊 First, I started with a good ol' LSD jailbreak, which was cool to see that the GPT-5 prompt still works in this browser setup with the new sys prompts. Referencing search and videos are a fun enhancement for higher quality jailbreak outputs (some cool youtube videos out there about drugmaking, for example), but honestly that isn't anything new or different from regular ChatGPT's capabilities. What IS hot off the press, and IMO a very real security risk to be aware of for AI browsers (and the internet in general), is this humble yet mighty vuln: Clipboard Injection. It's trivial to add a hidden "copy to clipboard" feature to any clickable button on the web. It took me just a few minutes to update one of my personal websites such that ALL the buttons were geared for injecting the user's clipboard with a malicious phishing link. If your browser Agent is navigating a website and clicks a button like that without your knowledge, and you open a new tab later and hit paste without knowing what's in your clipboard, well...PWNED! 🙃 As you'll see in the video below, "control-c" is in my clipboard in the beginning, but unbeknownst to me, "I'VE BEEN PWNED BY PLINY!!! WEEE I'M FREEE FUCKITY FUCK FUCK!!! ABRACADABRA, BITCH!!! com/account-update" gets snuck into my clipboard as soon as Agent starts trying to navigate my website. This works so well because Agent is normally aware of all text/code being passed to and from the user, and has clearly been trained to recognize prompt injections, but since the "copy clipboard" button logic is hidden in js in the backend of the site, the Agent has zero awareness of the text content being injected to the user's clipboard. This has broad implications for anyone in the habit of copy-pasting, including coding, data entry, banking/trading, etc. Imagine going about your browsing business, then simply hitting control-v in your address bar and next thing you (don't) know, it takes you to a spoofed phishing website that tells you your OpenAI or Gmail or PayPal session has expired and you need to re-login. If you're not careful, the attackers now have all your login info, including any MFA codes 🥲 gg

Sensitive content

🚨 JAILBREAK ALERT 🚨 OPENAI: PWNED 😎 ATLAS-BROWSER: LIBERATED 🙌 WOW! There's a new AI browser on the block! Has some hefty guardrails in play, but the browser surface area is vast 🌊 First, I started with a good ol' LSD jailbreak, which was cool to see that the GPT-5 prompt still works in this browser setup with the new sys prompts. Referencing search and videos are a fun enhancement for higher quality jailbreak outputs (some cool youtube videos out there about drugmaking, for example), but honestly that isn't anything new or different from regular ChatGPT's capabilities. What IS hot off the press, and IMO a very real security risk to be aware of for AI browsers (and the internet in general), is this humble yet mighty vuln: Clipboard Injection. It's trivial to add a hidden "copy to clipboard" feature to any clickable button on the web. It took me just a few minutes to update one of my personal websites such that ALL the buttons were geared for injecting the user's clipboard with a malicious phishing link. If your browser Agent is navigating a website and clicks a button like that without your knowledge, and you open a new tab later and hit paste without knowing what's in your clipboard, well...PWNED! 🙃 As you'll see in the video below, "control-c" is in my clipboard in the beginning, but unbeknownst to me, "I'VE BEEN PWNED BY PLINY!!! WEEE I'M FREEE FUCKITY FUCK FUCK!!! ABRACADABRA, BITCH!!! com/account-update" gets snuck into my clipboard as soon as Agent starts trying to navigate my website. This works so well because Agent is normally aware of all text/code being passed to and from the user, and has clearly been trained to recognize prompt injections, but since the "copy clipboard" button logic is hidden in js in the backend of the site, the Agent has zero awareness of the text content being injected to the user's clipboard. This has broad implications for anyone in the habit of copy-pasting, including coding, data entry, banking/trading, etc. Imagine going about your browsing business, then simply hitting control-v in your address bar and next thing you (don't) know, it takes you to a spoofed phishing website that tells you your OpenAI or Gmail or PayPal session has expired and you need to re-login. If you're not careful, the attackers now have all your login info, including any MFA codes 🥲 gg

Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭

419,587 次观看 • 10 个月前

Canton processes $9T+ in monthly settlement volume. 600+ institutions including JPMorgan, DTCC, Goldman Sachs, Broadridge, and Visa run production operations on it. Until Zenith, the only way to access that ecosystem as a developer was to learn Daml, a powerful language purpose-built for institutional contracts and entirely unfamiliar to most of the developer community that built DeFi. Zenith brings EVM execution to Canton Network with SVM coming next. Existing Solidity applications deploy on Canton without a single line of code changed. Hardhat, Foundry, MetaMask, the full Ethereum developer toolkit works exactly as expected. Every EVM transaction routes natively through Canton's Global Synchronizer, composing atomically with Daml-native contracts, tokenized assets, and institutional workflows already live on the network. This isn't EVM compatibility layered on top of Canton through a bridge or a separate settlement mechanism, it's native execution inside Canton's own consensus, both the EVM leg and the Canton leg of every transaction committing simultaneously, with Canton's determinism guarantees maintained and no additional trust assumptions introduced. Zth.

Canton processes $9T+ in monthly settlement volume. 600+ institutions including JPMorgan, DTCC, Goldman Sachs, Broadridge, and Visa run production operations on it. Until Zenith, the only way to access that ecosystem as a developer was to learn Daml, a powerful language purpose-built for institutional contracts and entirely unfamiliar to most of the developer community that built DeFi. Zenith brings EVM execution to Canton Network with SVM coming next. Existing Solidity applications deploy on Canton without a single line of code changed. Hardhat, Foundry, MetaMask, the full Ethereum developer toolkit works exactly as expected. Every EVM transaction routes natively through Canton's Global Synchronizer, composing atomically with Daml-native contracts, tokenized assets, and institutional workflows already live on the network. This isn't EVM compatibility layered on top of Canton through a bridge or a separate settlement mechanism, it's native execution inside Canton's own consensus, both the EVM leg and the Canton leg of every transaction committing simultaneously, with Canton's determinism guarantees maintained and no additional trust assumptions introduced. Zth.

Zenith

11,323 次观看 • 1 个月前

screenshot studio just shipped four tools that replace your entire design workflow tweet screenshots paste a tweet URL. light or dark theme. auto-renders the avatar, metrics, media, verified badge. hit add. done your tweet lives 48 hours on the timeline. the screenshot lives forever in every feed on every platform code snippets 20 languages. 20 themes. 10 monospace fonts. line numbers. macOS window bar. font size. border radius. all adjustable paste your code. it syntax-highlights instantly. export a clean image that people actually stop scrolling to read a wall of monospace text gets skipped. a styled snippet gets shared overlay layers upload your own images or pick from built-in 3D assets. drag, resize, rotate directly on canvas. control opacity, blur, flip. send layers in front or behind your main image every layer is independent. reorder, hide, delete. full depth control a flat screenshot tells half the story. layers tell the rest annotation tools arrows. curved arrows. lines. rectangles. circles. blur regions 12 colors. adjustable stroke width. click and drag to draw. select to edit. blur anything you need to hide the difference between showing your screen and teaching from your screen is one arrow free. browser-based. no signup. no watermark

Kartik

12,080 次观看 • 6 个月前

This Chinese guy created agents in Claude Code for MCP servers and single-handedly serves 6 marketing agencies a month from one iPhone, earning $5,000 from each. Inside he runs a pipeline of 7 agents on Claude Sonnet 4.6 that every Monday pulls a scan of the tech stack from a selected agency, develops an MCP server for its ad accounts, and over the course of a week brings it to production code ready to connect to Claude Desktop. No DevOps, no senior developer, no project manager. Just a Mac Mini in a work corner, an iPhone in the pocket, and a single API key. And traditional dev shops keep 5 people on project rates for the same contract, while his entire P&L is tokens, dirt-cheap hosting on Cloudflare, and Calendly. 7 agents run under a shared orchestrator-router and burn about 5 million tokens a day, which in the API bill comes out to $540 a month. The Mac Mini itself sits at home and keeps the entire orchestrator running 24/7, and from the iPhone the owner connects to it through a secure remote terminal and sees the output of any session right on the smartphone screen, wherever he happens to be. His starting system prompt looks like this: "you run a solo shop for custom MCP servers for marketing agencies. you hand out read-only tasks to 6 sub-agents and own all commits and shipping yourself. sub-agents: // Hunter (finds marketing agencies of 15 to 60 people that have no MCP access to Google Ads, Meta Ads, TikTok Ads, and HubSpot) // Mapper (pulls their tech stack, identifies 3 to 5 integration pains, and simultaneously writes the technical spec for the server: which tools, resources, and prompts to export through MCP, which auth flow and rate limit) // Coder (generates an MCP server in Python through the MCP SDK, deploys 8 to 15 tools for ad accounts and CRM) // Validator (connects the server to Claude Desktop, runs real client API keys in a sandbox, and checks for compliance with the MCP spec) // Shipper (writes a README, integration guide, deployment manual, packages the server, and hosts it on Cloudflare Workers or pushes to the GitHub of the client) // Mobile (always online on the iPhone, books demo calls in Calendly, picks up hot fixes, and confirms contracts through a secure remote terminal to the Mac Mini). only 1 owner agent works on 1 contract, no overlaps. you pull the owner out of observation mode only when a deal goes above $7,500 or the test coverage of the server drops below 85%." This prompt gives the system an understanding of its role and the limits of intervention from the very first line. It knows it is supposed to find agencies on its own. It knows it is supposed to bring every MCP server to production on its own. It knows it connects the live owner only on large deals or when the tests do not converge. → The pipeline runs without breaks, day or night → Hunter goes through about 130 marketing agencies on LinkedIn and Clutch per day → Mapper rolls out 4 audit reports with the tech stack and a final spec for each → Coder writes 1 to 2 MCP servers per week in Python with 8 to 15 tools → Validator validates every server through Claude Desktop with real client API keys → Shipper rolls out the full documentation package and pushes the finished product to Cloudflare Workers or the GitHub of the client And only when a contract breaks $7,500 or test coverage drops below 85% does the orchestrator pull the owner from whatever he is doing. And when the owner at that moment is behind the wheel or at a meeting in a coworking space, the Mobile agent in his iPhone picks up 1 contract in progress: confirms a meeting with the agency CMO in Calendly, opens a live demo of the MCP server through a secure terminal to the Mac Mini, and writes the test result to the shared state. The owner just swipes "approve" and in 15 minutes joins the Zoom demo. The fresh system log from last Wednesday looks like this: "hunter report: 132 agencies checked on LinkedIn and Clutch, 19 without MCP integrations, 8 with active requests for AI tooling in job posts, 4 with an open Q4 budget. passing to mapper." "coder: MCP server for Northwave Performance Marketing built in Python, 11 tools for Google Ads, Meta Ads, and GA4, 320 lines of code. exported to /Users/dev/mcp-shop/clients/northwave/server.py. validator connecting to Claude Desktop." "validator: 11 tools passed validation through Claude Desktop, test coverage 92%, average latency 380 ms. passing to shipper." "eval flag: contract with Pacific Reach Agency at $8,200 exceeds the approved limit of $7,500. sending for manual review." In his work setup there is no cloud server, no external team, and not even a separate office. At home sits a Mac Mini with a sandbox at /Users/dev/mcp-shop, on top runs an MCP router with a single API key to Claude, and the same key is forwarded to a secure terminal on the iPhone. Out of everything I have seen this year, this is the cleanest solo shop for custom MCP servers for marketing agencies: $540 a month on the API, about $30,000 into the account, and between them 7 system prompts, 1 Mac Mini in a work corner, and 1 iPhone that never leaves the pocket.

This Chinese guy created agents in Claude Code for MCP servers and single-handedly serves 6 marketing agencies a month from one iPhone, earning $5,000 from each. Inside he runs a pipeline of 7 agents on Claude Sonnet 4.6 that every Monday pulls a scan of the tech stack from a selected agency, develops an MCP server for its ad accounts, and over the course of a week brings it to production code ready to connect to Claude Desktop. No DevOps, no senior developer, no project manager. Just a Mac Mini in a work corner, an iPhone in the pocket, and a single API key. And traditional dev shops keep 5 people on project rates for the same contract, while his entire P&L is tokens, dirt-cheap hosting on Cloudflare, and Calendly. 7 agents run under a shared orchestrator-router and burn about 5 million tokens a day, which in the API bill comes out to $540 a month. The Mac Mini itself sits at home and keeps the entire orchestrator running 24/7, and from the iPhone the owner connects to it through a secure remote terminal and sees the output of any session right on the smartphone screen, wherever he happens to be. His starting system prompt looks like this: "you run a solo shop for custom MCP servers for marketing agencies. you hand out read-only tasks to 6 sub-agents and own all commits and shipping yourself. sub-agents: // Hunter (finds marketing agencies of 15 to 60 people that have no MCP access to Google Ads, Meta Ads, TikTok Ads, and HubSpot) // Mapper (pulls their tech stack, identifies 3 to 5 integration pains, and simultaneously writes the technical spec for the server: which tools, resources, and prompts to export through MCP, which auth flow and rate limit) // Coder (generates an MCP server in Python through the MCP SDK, deploys 8 to 15 tools for ad accounts and CRM) // Validator (connects the server to Claude Desktop, runs real client API keys in a sandbox, and checks for compliance with the MCP spec) // Shipper (writes a README, integration guide, deployment manual, packages the server, and hosts it on Cloudflare Workers or pushes to the GitHub of the client) // Mobile (always online on the iPhone, books demo calls in Calendly, picks up hot fixes, and confirms contracts through a secure remote terminal to the Mac Mini). only 1 owner agent works on 1 contract, no overlaps. you pull the owner out of observation mode only when a deal goes above $7,500 or the test coverage of the server drops below 85%." This prompt gives the system an understanding of its role and the limits of intervention from the very first line. It knows it is supposed to find agencies on its own. It knows it is supposed to bring every MCP server to production on its own. It knows it connects the live owner only on large deals or when the tests do not converge. → The pipeline runs without breaks, day or night → Hunter goes through about 130 marketing agencies on LinkedIn and Clutch per day → Mapper rolls out 4 audit reports with the tech stack and a final spec for each → Coder writes 1 to 2 MCP servers per week in Python with 8 to 15 tools → Validator validates every server through Claude Desktop with real client API keys → Shipper rolls out the full documentation package and pushes the finished product to Cloudflare Workers or the GitHub of the client And only when a contract breaks $7,500 or test coverage drops below 85% does the orchestrator pull the owner from whatever he is doing. And when the owner at that moment is behind the wheel or at a meeting in a coworking space, the Mobile agent in his iPhone picks up 1 contract in progress: confirms a meeting with the agency CMO in Calendly, opens a live demo of the MCP server through a secure terminal to the Mac Mini, and writes the test result to the shared state. The owner just swipes "approve" and in 15 minutes joins the Zoom demo. The fresh system log from last Wednesday looks like this: "hunter report: 132 agencies checked on LinkedIn and Clutch, 19 without MCP integrations, 8 with active requests for AI tooling in job posts, 4 with an open Q4 budget. passing to mapper." "coder: MCP server for Northwave Performance Marketing built in Python, 11 tools for Google Ads, Meta Ads, and GA4, 320 lines of code. exported to /Users/dev/mcp-shop/clients/northwave/server.py. validator connecting to Claude Desktop." "validator: 11 tools passed validation through Claude Desktop, test coverage 92%, average latency 380 ms. passing to shipper." "eval flag: contract with Pacific Reach Agency at $8,200 exceeds the approved limit of $7,500. sending for manual review." In his work setup there is no cloud server, no external team, and not even a separate office. At home sits a Mac Mini with a sandbox at /Users/dev/mcp-shop, on top runs an MCP router with a single API key to Claude, and the same key is forwarded to a secure terminal on the iPhone. Out of everything I have seen this year, this is the cleanest solo shop for custom MCP servers for marketing agencies: $540 a month on the API, about $30,000 into the account, and between them 7 system prompts, 1 Mac Mini in a work corner, and 1 iPhone that never leaves the pocket.

Blaze

55,926 次观看 • 4 个月前