PyTorch Single Controller

Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]

(ACL 2025 Main) Code for MultiAgentBench : Evaluating the Collaboration and Competition of LLM agents https://www.arxiv.org/pdf/2503.01935

Code for the manim-generated scenes used in welch labs videos

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Kimi K2 is the large language model series developed by Moonshot AI team

Project creating a proof-of-concept brain-computer interface from scratch.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

Benchmarking HASHIRU AI

The Expert Orchestrator AI: Dynamically Adapting, Budget-Aware, and Precisely Tailored to Your Needs

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"

A free and strong UCI chess engine

A programming framework for agentic AI

Model Context Protocol Servers

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

🏅 Collection of Kaggle Solutions and Ideas 🏅

An Extensible Deep Learning Library

PathwaysJob API is an OSS Kubernetes-native API, to deploy ML training and batch inference workloads, using Pathways on GKE.

xpk (Accelerated Processing Kit, pronounced x-p-k,) is a software tool to help Cloud developers to orchestrate training jobs on accelerators such as TPUs and GPUs on GKE.

A simple, performant and scalable Jax LLM!

Package of Pathways-on-Cloud utilities

This repository contain the simple llama3 implementation in pure jax.

A machine learning compiler for GPUs, CPUs, and ML accelerators

Fully open reproduction of DeepSeek-R1

AIOS: AI Agent Operating System

Code from the "CUDA Crash Course" YouTube series by CoffeeBeforeArch