Stars
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
A tutorial on modern GPU programming for machine learning systems
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, …
Agentic Kernel Optimization — advanced & eXtensible: a closed-loop, campaign-based multi-agent system for optimizing GPU kernels (benchmark-swappable; default flashinfer-bench).
Agentic Kernel Optimization for All — automated GPU kernel optimization for any kernel, any hardware, any language
Academic Research Skills for Claude Code: research → write → review → revise → finalize
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Codex skill for converting slide images, PDFs, and image-based PPTX files into editable PowerPoint decks.
GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents
ai副业赚钱大集合，教你如何利用ai做一些副业项目，赚取更多额外收益。The Ultimate Guide to Making Money with AI Side Hustles: Learn how to leverage AI for some cool side gigs and rake in some extra cash. Check out the English versi…
A Python DSL to write Nvidia PTX for Hopper and Blackwell in JAX and PyTorch
A CUDA kernel optimization toolkit for validation, benchmarking, Nsight Compute profiling, bottleneck analysis, and iterative tuning. It helps improve custom GPU operators with reproducible workflo…
Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”
An offline deep reinforcement learning library
This repository contains low-bit quantization papers from 2020 to 2026 on top conference.
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 170,000+ scientists worldwide. 161 ready-to-use validated skills plus 100+ scientific databases covering bio…
PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai
Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
A curated guide for LLM-agent-driven scientific research automation — from getting started to the frontier.
[ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)
AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,005+ agentic skills. Includes CLI, local MCP, cat…