An index of the LangChain + LangGraph ecosystem: concepts, projects, tools, templates, and guides for LLM & multi-agent apps.

A collection of MCP servers.

An invisible desktop application to help you pass your technical interviews.

Supercharge Your LLM with the Fastest KV Cache Layer

Progressive enhancement for HTML

Official Implementation of "KBLaM: Knowledge Base augmented Language Model"

Gemma open-weight LLM library, from Google DeepMind

Multi-Language Backend Framework that unifies APIs, background jobs, workflows, and AI Agents into a single core primitive with built-in observability and state management.

AI Tensor Engine for ROCm

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of …

VIP cheatsheet for Stanford's CME 295 Transformers and Large Language Models

Fork of the Triton language and compiler for Windows support and easy installation

Benchmarking Large Language Models for FHIR

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

Model Context Protocol Servers

A modern chat interface that provides a unified experience for interacting with multiple AI models. The application supports seamless integration with leading AI providers including OpenAI, Anthrop…

Cost-efficient and pluggable Infrastructure components for GenAI inference

DeepTeam is a framework to red team LLMs and LLM systems.

An Open-source RL System from ByteDance Seed and Tsinghua AIR

A Datacenter Scale Distributed Inference Serving Framework

An extension of the nanoGPT repository for training small MOE models.

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Understanding Deep Learning - Simon J.D. Prince

A Python based lightweight robot simulator for the development of algorithms in robotics navigation, control, and learning.

Deploy and share agents with open infrastructure, free from vendor lock-in.

NVIDIA curated collection of educational resources related to general purpose GPU programming.