Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

Experimental exploration of skills discovery and distribution through MCP primitives. Maintained by the Skills Over MCP Working Group.

Claude Code Snapshot for Research. All original source code is the property of Anthropic.

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

An extremely fast Python package and project manager, written in Rust.

Trace Context

A collection of sample agents built with Agent Development Kit (ADK)

Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!

Deep Learning for humans

An ML Systems Onboarding list

Streaming Anomaly Detection Solution by using Pub/Sub, Dataflow, BQML & Cloud DLP

Complete solutions to the Programming Massively Parallel Processors Edition 4

NCCL Tests

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Learning material for CMU10-714: Deep Learning System

Material for gpu-mode lectures

如何成为一名自洽的程序员

Repository for the book "Crafting Interpreters"

Defines standards for generating consistent, accessible telemetry across a variety of domains

Self-hosting PL/0 to C compiler to teach basic compiler construction from a practical, hands-on perspective.

High-performance In-browser LLM Inference Engine

Rust implementation of gRPC

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Distribute and run LLMs with a single file.

Stanford CS 110L Spring 2020 assignment starter code