Sharing early versions of Ada, a personal AI Assistant built on OpenAIs Realtime API

Node.js + JavaScript reference client for the Realtime API (beta)

Testing baseline LLMs performance across various models

Extracted Maps of the DOS Game Test Drive 3

A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

Code and Data for Tau-Bench

Concise UI Tests with Java!

The best OSS video generation models

Build AI Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI.

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

Blazingly fast LLM inference.

React app for inspecting, building and debugging with the Realtime API

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

Entropy Based Sampling and Parallel CoT Decoding

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

The first real AI developer

Over 325 terminal color schemes/themes for iTerm/iTerm2. Includes ports to Terminal, Konsole, PuTTY, Xresources, XRDB, Remmina, Termite, XFCE, Tilda, FreeBSD VT, Terminator, Kitty, MobaXterm, LXTer…

React app for inspecting, building and debugging with the Realtime API

A simple 2D implementation of Radiance Cascades by Alexander Sannikov in Unity

Golang float16/bfloat16/float8 provides IEEE 754 half-precision format (binary16) with correct conversions to/from float32

plusminus13 - a js13kGames 2024 competition entry by @jure.

rollermaze - a js13kGames 2024 competition entry by @picosonic.

We write your reusable computer vision tools. 💜

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

Brand new TTS solution

High accuracy RAG for answering questions from scientific documents with citations