A kernel library written in tilelang

An Evidence-Graded Catalog of Benchmarks for LLM Kernel Agents

Run Claude Code across multiple Claude accounts — a transparent proxy that auto-switches on quota and minimizes prompt-cache rebuilds

Reference code for the Meta-Harness paper.

CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.

Surgical GPU kernel benchmark: 7 hard problems, frontier coding agents, roofline-graded against hardware peak.

A Claims-Annotated Catalog of LLM-Driven Kernel Generation Systems

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Multi-account Claude proxy with automatic quota-based rotation

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

From Automated Idea Factory to Realization

Public skills collected from well-known open-source projects focused on LLM infrastructure, GPU kernels, compiler/operator development

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.

PTO instruction set architecture

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chem…

kernelbench.com — GPU kernel engineering benchmarks for autonomous LLM coding agents. v3 archive + v-hard latest.

⚡ Clash for Lab 是为实验室环境设计的科学上网工具，无需sudo权限，优雅地一键式脚本安装

[ICML2026] Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation

🌟本项目自动抓取并索引科学空间的文章元数据，按研究主题进行规则分类，方便在 GitHub 上快速浏览并跳转到原文。

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Summary of some awesome work for optimizing LLM inference

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.