FlashMLA: Efficient Multi-head Latent Attention Kernels
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.
Production-ready platform for agentic workflow development.
This repository contains the Hugging Face Agents Course.
A simple screen parsing tool towards pure vision based GUI agent
Integrate the DeepSeek API into popular software
Master programming by recreating your favorite technologies from scratch.
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
The trust-minimized, zero-knowledge bridging protocol, designed for censorship resistance, extremely high security, and usage in decentralized finance.
DeepEP: an efficient expert-parallel communication library
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Open-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshooting.
The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
🪄 Create rich visualizations with AI
🤗 smolagents: a barebones library for agents that think in code.
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
Easily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM!
🧠「大模型」2小时完全从0训练64M的小参数LLM!Train a 64M-parameter LLM from scratch in just 2h!
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling