Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

A comprehensive, step-by-step guide to learning Machine Learning from absolute basics to advanced topics

Quran bil-Quran: Root-based verse connections dataset with semantic families and web reader app

The first computational Quran-Hadith concordance (96.3% root coverage, 1.5M links) and the largest open-source narrator database (115,735 profiles from 22 classical texts, 72.6% graded). Bukhari 99…

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

Machine-readable Uyghur headword lists released as open data to support digital infrastructure and linguistic preservation against ongoing systematic erasure.

Generic framework components for blockchain remittance platforms, open sourced by BarqChain

CINO: Pre-trained Language Models for Chinese Minority (少数民族语言预训练模型)

Open-source, self-hosted Clay alternative for lead sourcing, enrichment waterfalls, AI research, buying signals, and outbound automation.

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

Voice Operation and Design Engine with Reproduction capabilities

Turn your own PDF textbooks into an AI-searchable knowledge base and structured, fully-cited notes — figures included. Local-first, token-frugal.

🙌 OpenHands: AI-Driven Development

Complete installable LLM for edge devices or hardware systems

State-of-the-art 1B OCR model - Local version of HuggingFace demo. Created by Claude Code, orchestrated by TheAwakenOne619.

Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models

A native Rust toolkit for OCR, document layout analysis, and vision-language document understanding.

PP-OCRv5 multi-language ONNX models with embedded character dictionaries — extracted from PaddleOCR/RapidOCR

📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.

tiny vision language model

An open source, modular, lightweight, and extensible RAG application stack, designed for anyone and everyone.

A collection of scientific methods, processes, algorithms, and systems to build stories & models.

MLX-accelerated Surya OCR on Apple Silicon (~3.6x faster), for electoral-roll parsing

Lightweight text and scans processing: embedding, document processing, OCR, OMR, etc, with inference via ggml in pure C++

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

VibeCurb - Injects taste into AI workflows to stop agents from generating boring, AI slop.

An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.