Native and Compact Structured Latents for 3D Generation

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Running Docling as an API service

Mechanistic understanding and validation of large AI models with SemanticLens

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Modelio is a modeling solution offering a wide range of functionalities based on the main standards of enterprise architecture, software development and systems engineering.

Python package for graph statistics

Streamlit UI for Microsoft GraphRAG, with post-processing for source citations.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Rivet plugin for integration with Ollama, the tool for running LLMs locally easily

🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).

SoTA open-source TTS

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Get your documents ready for gen AI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing…

pdfalign is a very simple tool to grid align extracted pdf text. This is useful for invoice table extraction or further processing with llms / rag systems

This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented Generation (RAG) pipeline.

Build and run containers leveraging NVIDIA GPUs

A Repo For Document AI

A rust library for extracting content from pdfs

Split text into semantic chunks, up to a desired chunk size. Supports calculating length by characters and tokens, and is callable from Rust and Python.

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

KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation