Text-Extract-API: Turning Documents into Structured Data Without the Headache
Ever needed to extract data from a PDF or scanned document? Text-extract-api offers an elegant solution combining modern OCR and language models.
Language
HomeLanguages
Sections
Ever needed to extract data from a PDF or scanned document? Text-extract-api offers an elegant solution combining modern OCR and language models.
BlenderGPT integrates GPT-4 into Blender, converting English commands into Python code. Learn how this addon transforms 3D modeling workflows.
Meet Alerta — an open-source platform that turns alert chaos into an organized workflow. Supports Grafana, Zabbix, Prometheus, and more.
MLX-Audio brings lightning-fast TTS, STT, and STS capabilities to Apple Silicon Macs. Built on Apple's MLX framework, it offers Whisper, Kokoro, voice cloning, and more—all running locally without cloud costs.
DeepFloyd IF is a modular image generation system from Stability AI that uses a cascade of three models to create photorealistic images from text.
AI Data Science Team by Business Science automates routine Data Science tasks with specialized AI agents and a visual pipeline builder.
ClatScope is a Python OSINT utility with 70+ features that checks emails for breaches, scans 250+ platforms by username, and builds automated person profiles.
Coldtype is an experimental Python library for programmable typography that turns code into visual masterpieces. Perfect for animated text and generative design.
Discover ddgr, the command-line DuckDuckGo search tool that developers are loving for its privacy features, terminal-first workflow, and powerful Bang commands.
Maple Mono is an open-source monospaced font designed to make coding smooth and pleasant. With smart ligatures, Nerd-Font support, and deep customization, it's worth trying.
Exodus by Intoli transfers Linux binaries with all dependencies between systems without containers. One command does it all.
OpenAI Whisper is an open-source speech recognition model that transcribes and translates audio in multiple languages locally. Here's how to get started.
vimGPT combines GPT-4V with Vimium to let AI see web pages and click links. A fascinating experiment in multimodal AI and browser automation.
NVIDIA's Model Optimizer open-source tool unifies quantization, pruning, and distillation for efficient LLM deployment with TensorRT-LLM, vLLM, and SGLang.
Andriller CE is a Python-based forensic toolkit for Android devices that extracts data, bypasses locks, and analyzes app backups including encrypted WhatsApp databases.
Tired of wrestling with multiple fitness APIs? Open Wearables is an open-source platform that unifies data from Garmin, Apple Health, Whoop, and more into a single API.
DeepFaceDrawing transforms simple face sketches into photorealistic portraits using neural networks. It works with rough sketches, making generative AI accessible to everyone.
Discover Free-TV/IPTV, a curated M3U playlist of free, legal TV channels from around the world. Perfect for developers, travelers, and anyone tired of subscriptions.
Keras 3 unifies TensorFlow, PyTorch, and JAX in one framework. Get up to 350% performance boost by switching backends with a single line of code.
Turn your Telegram into a remote terminal with Claude Code integration. Manage projects, run tests, and automate workflows from anywhere.
NoScribe is a local AI-powered transcription tool that converts speech to text with impressive accuracy. Perfect for researchers, journalists, and podcasters.
Grok-1 is xAI's massive open-source LLM with 314B parameters and MoE architecture, now available for researchers and ML engineers to explore.
Neural Photo Editor lets you paint on photos while neural networks generate realistic continuations. Great for designers, researchers, and GAN enthusiasts.
Videomass is a cross-platform, open-source GUI for FFmpeg that makes video processing accessible without memorizing complex commands.