Stars
A powerful command-line OCR tool built with Apple's Vision framework, supporting single image and batch processing with detailed positional information output.
Wan: Open and Advanced Large-Scale Video Generative Models
OCR powered screen-capture tool to capture information instead of images
Composable building blocks to build Llama Apps
Code for the paper "FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents" arXiv:2502.07393
The first autonomous computer program that can do anything to earn money without human operators.
Code for ACM RecSys 2023 paper "Turning Dross Into Gold Loss: Is BERT4Rec really better than SASRec?"
OnboardingKit is a Swift SDK that helps you create onboarding experiences in Swift and SwiftUI.
Sky-T1: Train your own O1 preview model within $450
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
The 2013 edition of the Source SDK
This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"
MoBA: Mixture of Block Attention for Long-Context LLMs
A simple screen parsing tool towards pure vision based GUI agent
Implementation of the proposed DeepCrossAttention by Heddes et al at Google research, in Pytorch
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper
Source code for NoteLLM and NoteLLM-2
[WWW 2025] Official PyTorch Code for "CTR-Driven Advertising Image Generation with Multimodal Large Language Models"