Lightweight coding agent that runs in your terminal

Run Claude Code on OpenAI models

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

A Tiny Terminal Chat App for AI Models with MCP Client Support

Efficient Triton Kernels for LLM Training

Getting crystal-like representations with harmonic loss

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

Witness the aha moment of VLM with less than $3.

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Make websites accessible for AI agents

Database of Steam video game data from October 2024, including game details, genres, reviews, tags, and SteamSpy insights

Out-of-the-box (OOTB) GUI Agent for Windows and macOS

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

A playbook for systematically maximizing the performance of deep learning models.

Curate better data for LLMs

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

ComfyUI nodes to edit videos using Genmo Mochi

A fork of Anthropic Computer Use that you can run on Mac computers to give Claude and other AI models autonomous access to your computer.

Build production-ready AI agents in both Python and Typescript

smolLM with Entropix sampler on pytorch

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Fast and accurate automatic speech recognition (ASR) for edge devices