infodagang.com

Bir geliştirici, DeepSeek-OCR tabanlı, hafif ancak güçlü bir OCR ön uç uygulaması olan deepSeek_ocr_app'i oluşturdu ve uygulama artık açık kaynak kodlu. Temiz ve sezgisel bir arayüze sahip; uygulamayı başlatmak için görüntüleri sürükleyip bırakmanız yeterli. Tek dosya boyutu 100 MB'a kadar olabilir. En yaygın OCR senaryolarını kapsayan dört temel mod içerir: düz metin çıkarma, görüntü açıklaması, belirtilen içerik araması ve özel öneri işleme. GitHub: github.com/rdumasia303/de… Görsel sınırlayıcı kutu gösterimini destekleyerek, tanınan alanı ve koordinatları bir bakışta netleştirir. Sonuçlar HTML veya Markdown olarak dışa aktarılabilir; Docker ile tek tıklamayla dağıtılabilir ve karmaşık yapılandırma gerektirmeden kullanıma hazırdır.

¿Cansado de pagar por Spotify? OpenSpot: la app de música 100% GRATIS, open source, SIN ANUNCIOS y SIN LOGIN que está rompiéndola. ✅ Streaming en alta calidad ✅ Descargas offline ✅ Reproducción en segundo plano ✅ Likea y guarda tus temas ✅ Sin cuentas ni rastreo REPOOO👇

Online video editor with real-time preview github.com/mohyware/clip-…

Sends WhatsApp messages via REST API github.com/felipeDS91/wha…

lu kalo pengen dapet VPS murah saran gua beli di Tencent cloud dah mayan njir 10$ setahun jatohnya kek perbulan cuman 0,84$ 💥 speknya lumayan pula buat masukin ai agent agak banyak juga aman gua pembayarannya pake bank jago biar cepet caranya gua taro komen yak 👍

Multi-agent AI sales team for Claude Code github.com/zubair-trabzad…

OSINT: Gathering Information on a WhatsApp Account A phone number alone can reveal profile photos, status updates, and linked devices. Our guide shows exactly how you can legally and effectively extract intelligence from WhatsApp accounts! hackers-arise.com/open-source-in… @three_cube

Open source research automation platform github.com/Prismer-AI/Pri…

Self-hosted open source quiz platform github.com/Ralex91/Rahoot

Fine-tune DeepSeek-OCR on your own language! (100% local) Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. It is a 3B-parameter vision model that achieves 97% precision while using 10x fewer vision tokens than text-based LLMs. In fact, you can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet, which includes the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

🚨 BREAKING: You can now get Gemini Pro FREE for a full year. Previously priced at $200/year — now it’s 100% free. No payment required. Here’s how to activate it in 3 simple steps 👇

Enterprise AI platform for workplace search and automation github.com/pipeshub-ai/pi…

Open source learning management system with mobile access github.com/classroomio/cl…

Web-based project management with GitHub integration github.com/opf/openproject

Offline audio and video transcription with Whisper github.com/thewh1teagle/v…

High-performance web scraping framework in Go github.com/tech-engine/go…

Open-source headless Node.js CMS for professional publishing github.com/TryGhost/Ghost

Centralized web dashboard for managing OpenClaw agents and jobs github.com/grp06/openclaw…

Automated SEO skills for Claude Code github.com/inhouseseo/sup…

gila, Claude Desktop sekarang bisa pake model pihak ketiga. artinya, lo bisa pake GPT-5.5, Gemini, DeepSeek, semua di UI Claude Desktop. ga perlu login ChatGPT, ga perlu switch app. cara setup: 1. Help > Troubleshooting > Enable developer mode 2. Developer > Configure Third-Party Inference 3. pake OpenRouter: - Connection: Gateway - Gateway base URL: openrouter.ai/api - Gateway API key: [API key OpenRouter lo] - Gateway auth scheme: x-api-key 4. restart done. UI Claude, brain model apa pun. save dulu.