A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

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

NVIDIA Isaac GR00T N1.5 - A Foundation Model for Generalist Robots.

Use late-interaction multi-modal models such as ColPali in just a few lines of code.

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

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

An example of multi-agent orchestration with llama-index

All the demos in my Youtube Channel: Yeyu Lab

Large Action Model framework to develop AI Web Agents

A collection of Awesome Google Dorks.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.

Using GPT to parse PDF

Technically-oriented PDF Collection (Papers, Specs, Decks, Manuals, etc)

Developer samples for the KDB.AI vector database

A conda-forge distribution.

Examples and guides for using the OpenAI API

A programming framework for agentic AI

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progres…

Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

DSPy: The framework for programming—not prompting—language models

Apply a Style Transfer Neural Network in real time with Unreal Engine 5 leveraging ONNX Runtime.

Using the NEAT algorithm to train an AI to play pong in Python!

RL Reach is a platform for running reproducible reinforcement learning experiments.

OpenAI Gym environment solutions using Deep Reinforcement Learning.

This is a solution for the second project of the Udacity deep reinforcement learning course. It includes code for training an agent and for using it in a simulation environment.

Implementation of TRPO and related algorithms