Stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
[Support 0.49.x]（Reset Cursor AI MachineID & Bypass Higher Token Limit） Cursor Ai ，自动重置机器ID ， 免费升级使用Pro功能: You've reached your trial request limit. / Too many free trial accounts used on this machi…
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous …
Free and Open Source Enterprise Resource Planning (ERP)
AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
TradingAgents: Multi-Agents LLM Financial Trading Framework
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
A configuration framework that enhances Claude Code with specialized commands, cognitive personas, and development methodologies.
Toolkit for linearizing PDFs for LLM datasets/training
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 17+ clouds, or on-prem).
Composable building blocks to build Llama Apps
g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains
No non-sense and no BS repo for how data structure code should be in Python - simple and elegant.
o1-engineer is a command-line tool designed to assist developers in managing and interacting with their projects efficiently. Leveraging the power of OpenAI's API, this tool provides functionalitie…
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
A free Python-distribution for Windows platform, including prebuilt packages for Scientific Python.
Docker images for production and development setups of the Frappe framework and ERPNext
HyperGen - Optimized inference and fine-tuning framework for diffusion (image & video) models. Up to 3x faster & 80% less VRAM.
This is submit50, CS50's command-line tool for submitting problems.