RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

PyTorch native post-training library

Cache-Augmented Generation: A Simple, Efficient Alternative to RAG

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 …

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

The Memory layer for your AI apps

Get your documents ready for gen AI

A natural language interface for computers

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Hunt down social media accounts by username across social networks

The provided Python program, Nim-Backdoor.py, generates a Nim program that operates as a backdoor, allowing remote command execution via a netcat-like session. This tool is designed to work on both…

DeepSeek Coder: Let the Code Write Itself

Enhanced ChatGPT Clone: Features OpenAI, Assistants API, Azure, Groq, GPT-4 Vision, Mistral, Bing, Anthropic, OpenRouter, Vertex AI, Gemini, AI model switching, message search, langchain, DALL-E-3,…

Accurately Locate Smartphones using Social Engineering

🕌 Muslim Board Browser Extension

[NeurIPS 2023 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.

📐 Jekyll theme for building a personal site, blog, project documentation, or portfolio.