Google Translate is cooked after this. A developer built... a local AI translation engine that runs 40 languages entirely on your own laptop. It's called LibreTranslate. No API key. No usage limits. No sending your documents to Google's servers. You install it once. It runs forever. Here's what it handles: → Paste text. Translated instantly. → Drop in a file. Outputs the translated version. → Point it at a URL. Returns the page in your language. → Build it into your own app via its local REST API. The speed is not the story. The privacy is. Google Translate reads every sentence you paste into it. Legal contracts. Medical records. Internal emails. Client documents. Every word goes to their servers and stays there. LibreTranslate runs entirely offline. Nothing leaves your machine. Ever. The numbers: → 40 languages supported → Runs on CPU -- no GPU needed → Self-hosted in under 5 minutes → REST API built in for developers → 10K+ stars on GitHub 100% open source. MIT licensed. Price: $0. Google charges nothing for Translate either but it charges you something else. GitHub:show more

Woow Tencent has released a model 100% open source... which is better than Google Translate... And it runs locally on your phone?! - Only 440MB (!!) - 33 languages - On-device translation So we have now a local Google Translate which is running completely offline. They are using AngelSlim which their compression toolkit. That's why the model is so efficient.show more

Someone just built a desktop app that that generates... 3D models from images and runs 100% locally. It's called Modly. It runs entirely on your GPU, no cloud, no API bills. Just drop an image and get a 3D mesh. 100% Open Source.show more

this is the worst local AI will ever be.... tomorrow it gets faster. next month the models get smarter. next year your GPU runs what a data center runs today. Qwen3.5-35B-A3B on a single 3090. told it to visualize its own expert routing. 256 experts, 8 active per token, rendered in 3D on the same GPU running inference. no API key. no subscription. no permission needed. closed AI isn't losing ground. it's losing the argument.show more

Cancelled ChatGPT -> Built JARVIS -> Pays $0 ->... it works offline + it's smarter than the $20/month version. No WiFi needed, no cloud, no API keys, no rate limits, no queues, no $20/month just to ask a server in Virginia for the weather. Just a local model running directly on the laptop hardware, voice activated, system integrated, controlling apps, answering questions, doing the work. Iron Man had JARVIS embedded in his suit, this guy has it embedded in his MacBook and it works on a plane, in a basement, on a remote cabin with zero signal. OpenAI is burning $700,000 a day on infrastructure to deliver something this guy runs for free. Anthropic charges $200/month for unlimited Claude access, microsoft built Copilot into every product they sell. This guy skipped all of it, downloaded a model and made his laptop the smartest device in the room. No subscription. No login. No internet. No data sent anywhere ever. The most powerful AI assistant on earth is now the one running locally on hardware you already own. ChatGPT charges you to think slower, he pays nothing and thinks alone, he made it himself.show more

1.7 billion free tokens per month. A month ago... i showed you how to route claude code through free providers. someone just shipped the cleanest version of this setup yet… it's called Freellmapi 13,400+ stars on github, MIT licensed, takes 2 minutes to install. what it does: stacks the free tiers of 16 different LLM providers behind one local API. point claude code, codex, or cursor at that one endpoint, and it automatically routes your calls across all 16 free pools. The 16 providers it covers: Google, Groq, Cerebras, Mistral, OpenRouter, GitHub Models, Cloudflare, Cohere, NVIDIA, HuggingFace, Ollama Cloud, Kilo, Pollinations, LLM7, OVH, and OpenCode Zen. if you sign up to all 16 and add your free API keys, you get roughly 1.7 billion free tokens per month combined. ▫️ How to install (one command) curl -fsSL bash this runs the whole thing locally on your machine through Docker. once it's up, open paste your provider keys on the Keys page, and grab the unified API key from the dashboard. that's the key you point your apps at. With this, claude code stops hitting your monthly cap because every prompt routes through the 16 free pools instead of your paid plan. and if one provider rate-limits mid-conversation, freellmapi falls over to the next one automatically so your session never breaks. repo: Free, MIT-licensed, runs on your laptop or a $5 VPS.show more

Mika is now open source: a real phone agent... that runs on your Android phone. Tell it what you want, and it gets it done in your apps and on the web, on a hidden background screen while you keep using your phone. No root, no computer, your own logins. In the videos, asked in plain English: • Amazon: find a USB-C charger under $30 with 4.5★+, add it to the cart, stop before checkout • Google Flights: cheapest nonstop SFO → New York next Friday • Hacker News: top 5 stories with points, in 22 seconds What's inside: • Operates any app on your phone, no per-app setup • Built-in browser for search, filters and batch work • Floating capsule you can call up from any app • Local Linux sandbox for Python and your files Bring your own model key (OpenAI, Anthropic, Gemini, DeepSeek, Qwen and more). Apache-2.0. Star it, download the APK, or build it with me:show more

COPY is live on Robinhood Chain $COPY CA: 0xac79255f6f404eba14f316e8669d76573a2d7b1e... Five walls read a setup before you copy it: how strong the source is, how deep the pool is, whether the market actually turns over, whether the move is still inside the band, and whether there is a fresh mark to trade against. EDGE, DEPTH, TURN, MOMO, PRICE. A wallet you follow buying is not a reason. Most setups die on the first wall, and you get the exact wall that refused it, every time. Every decision is printed. The terminal runs from one process, keeps local state, and half of it needs no key at all. It never predicts a price. It tells you what you would actually be copying. Open source, MIT, runs on your machine. No browser wallet, nothing signs.show more

NEW | NEWYDD You can now use Canva to... translate the text on your designs. And yes, it has Welsh translation capabilities 🙌🏴󠁧󠁢󠁷󠁬󠁳󠁿 It can translate English to Welsh and Welsh to English. I've tested it, and it gives Google Translate a run for its money. 🧵show more

1 mini PC that fits in a palm, with... no monthly token bill attached to it. Most people run their AI through a browser tab. Every prompt, every document, every half-finished idea leaves the machine and lands on someone else's server. This ORICO mini PC runs the model locally. The assistant lives inside the box, not in a data center 2,000 miles away. Small enough to slide into a bag. Powerful enough that you stop noticing it is not a desktop. You pay once for hardware instead of every month for limits. No outage that takes your assistant down with it. No terms of service deciding what your files are worth. Plug it in anywhere, and the assistant is already there, offline, waiting. The smallest machine on the desk is the only one that keeps its mouth shut.show more

I just built a Google Ads Builder in Claude... Code that turns one URL into a complete, launch-ready campaign 🤯 Point it at your website and it builds the whole Google Search campaign — keywords, ad groups, every headline, the negative list — structured the way a good paid-search manager would. All inside Claude Code. Perfect for DTC brands and agencies who need Search live but don't have days to build it right. If you're staring at a blank Google Ads account, researching keywords one browser tab at a time, writing 15 headlines per ad group to a 30-character limit, guessing at a negative list while budget quietly leaks on junk clicks... This builds the entire campaign from a single input — your homepage URL: → Reads your site and works out what you sell and who for → Groups keywords into tight, high-intent ad groups → Writes every Responsive Search Ad — 15 headlines, 4 descriptions, to Google's exact limits → Builds a negative-keyword list so you stop paying for junk clicks → Adds sitelinks, callouts, match types, bidding, and a budget split → Exports a Google Ads Editor CSV you import in one click No blank-account paralysis. No keyword rabbit holes. No character-counting 60 headlines by hand. What you get: → A launch-ready campaign from just your URL → Tight ad groups built for Quality Score, not a keyword dump → Every ad written to Google's limits and policy → A one-click CSV import plus a full campaign dashboard Built 100% in Claude Code. No API keys, no Google Ads login. And I'm not sending a playbook this time — I'm giving the whole skill away for free. The actual file. Install it and build your own campaign in 5 minutes. Want the skill? > Like this post > Comment "BUILD" And I'll send it over (must be following so I can DM)show more

I explored a further possibility with local models: Qwen3.6... 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself. It's fully screenshot-based, so no Accessibility API needed. If it's on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.show more

This free tool lets Claude scrape Google Maps for... you, on autopilot. It's called Google Maps Scraper Kit. Give Claude a city and a business type, and it drives a local scraper to hand back a clean list of businesses, names, phones, emails, websites, ratings, and reviews. → One-command setup, runs entirely on your laptop → Claude Code skill triggers on plain language → Optional social media lookup at no extra cost → Built-in rate-limit safeguards and proxy support for larger jobs 100% Free. Open source.show more

🤯 Wow I can't believe I'm open sourcing the... email platform we built internally. Self-hosted, runs on your own AWS SES. You pay Amazon Web Services $0.10 per 1,000 emails instead of a SaaS markup, and your email data never leaves your infra. MIT licensed. Here's what it does 🧵show more

THIS FEELS ILLEGAL AND I LOVE IT A GitHub... repo with 61,030 stars defeats Google's Play Integrity check. GPL-licensed and last updated eight days ago. The repo is called Magisk. It roots your Android phone and hides root from banking apps. It runs Netflix on a phone the Play Store says is uncertified. Also, passes the same fraud detection Google built to stop it. Here is the part nobody is talking about. ↳ The man who built it is John Wu. ↳ He has been maintaining Magisk for nine years. Since November 2023 he has been a Senior Software Engineer at Google. On the Android Platform Security team. The exact team that builds Play Integrity. Google hired the person who defeats their root detection. He still ships the tool that defeats it. The repo is still online after nine years, hasn’t been taken down, and you should not install it because your phone is supposed to belong to Google.show more

Holy shit... Microsoft open sourced an inference framework that... runs a 100B parameter LLM on a single CPU. It's called BitNet. And it does what was supposed to be impossible. No GPU. No cloud. No $10K hardware setup. Just your laptop running a 100-billion parameter model at human reading speed. Here's how it works: Every other LLM stores weights in 32-bit or 16-bit floats. BitNet uses 1.58 bits. Weights are ternary just -1, 0, or +1. That's it. No floats. No expensive matrix math. Pure integer operations your CPU was already built for. The result: - 100B model runs on a single CPU at 5-7 tokens/second - 2.37x to 6.17x faster than llama.cpp on x86 - 82% lower energy consumption on x86 CPUs - 1.37x to 5.07x speedup on ARM (your MacBook) - Memory drops by 16-32x vs full-precision models The wildest part: Accuracy barely moves. BitNet b1.58 2B4T their flagship model was trained on 4 trillion tokens and benchmarks competitively against full-precision models of the same size. The quantization isn't destroying quality. It's just removing the bloat. What this actually means: - Run AI completely offline. Your data never leaves your machine - Deploy LLMs on phones, IoT devices, edge hardware - No more cloud API bills for inference - AI in regions with no reliable internet The model supports ARM and x86. Works on your MacBook, your Linux box, your Windows machine. 27.4K GitHub stars. 2.2K forks. Built by Microsoft Research. 100% Open Source. MIT License.show more

Run open models like Gemma 4 completely offline in... the Antigravity SDK. Built on Google AI Edge’s LiteRT, you can now run Gemma 4 directly on your local GPU. Zero API costs, total data privacy, and no internet required.show more

Fable 5 is INSANE for creating ads i built... an agent that studies your competition and thousands of viral ads, then gives you a full viral blueprint for your brand to copy just feed it a product photo and a landing page link and competitors names, 3 minutes later you've got a proven creative playbook for your ads, here's how it works: - scans your brand's own website (copy, offers, structure, CTAs) - scans competitor websites (you list them, or Claude finds likely ones for you) - pulls live ad data straight from Meta Ad Library + TikTok via spytools - extracts proven hooks, scripts, and visual/creative patterns from every source - synthesizes everything into one swipe-file library - output is a ready-to-paste doc, drop it into Claude and generate new ad scripts from proven angles instantly - runs locally, one command, your own API keys, no video generation step slowing you down runs 100% local, without $300/mo on spytool subscriptions or agency fees, full control, and API cost only RT + reply w/ "AGENT" and i'll send it to you so you can use it for your brand (must follow so i can DM)show more

🚨 YOUR AI AGENT CAN NOW READ YOUR NOTIFICATIONS... AND ACT ON THEM BEFORE YOU EVEN SEE THEM It’s called PhoneUse and it just launched. It gives your agent its own phone in the cloud, a real Android, connected to Claude through an MCP. Time needed: 10 minutes Steps: connect the MCP, tell your agent what to watch for What it handles on its own: → Your flight gets delayed: it sees the push notification and texts whoever is picking you up → Your Uber is on the way: it checks the driver’s status and lets people know when you’ll arrive → An app asks for a 2-step code: it reads the SMS and gets through the verification → An old app with no API: it opens it and taps through it like a person would Until now agents were stuck in the browser. Most of the apps we use every day don’t have an API, so they couldn’t touch them. Now they have a phone. Save it before it gets deleted 🔖 Link in the comments 👇show more

Grok 4.5 is now in Codex now too. No... API key, no billing setup, no config file. If you have X Premium, you sign in with your X account and Grok 4.5 runs inside your Codex. OAuth handles it. Your subscription is your access. That's it. And Grok 4.5 just got a lot better, so if you already pay for X Premium, you can now run it in Codex for free.show more

I built a 1-click deploy for Hermes Agent No... terminal, no Docker, no API keys. In one click it: → Spins up a dedicated cloud container → Configures Hermes with persistent memory & 70+ skills → Connects it to your Telegram bot → Goes live in under 60 seconds Your own AI agent that learns, creates skills, and gets smarter the longer it runs. Reply "HERMES" + RT and I'll send you the link (must be following so I can DM)show more