- Hong Kong
- blog.moephoto.tech
Stars
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a querya…
solosw / Trae-proxy-go
Forked from zhiquanchi/Trae-proxy-go使用golang编写的,为trae进行openai格式兼容的llm服务进行代理的软件。
Encapsulate the local Ollama into an OpenAI-compatible API to bypass the fixed model limitations in IDEs like TRAE.
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
AI for remote sensing, remote sense, object detection, oriented object detection, computer vision, cv
你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
A structured Claude Code workflow to reformat research manuscripts for any journal's submission requirements without altering scientific content, created by Chen Zhu 朱晨 | 遗传社科研究.
AI agents running research on single-GPU nanochat training automatically
🐧 一个更完整、更优雅的 Linux Clash / Mihomo 代理运行平台
[CVPR2026] Detect Anything via Next Point Prediction
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
an OpenClaw skill that can generate paper search-review-critque expert-agent relevant to specific topics (we use Scientific ML and 3D geometry surrogate modeling as a demo).
统一搜索工具集 - 跨平台内容搜索解决方案,支持 B 站/抖音/小红书/GitHub/Twitter 等 20+ 平台
A collection of Awesome Finance Agent Skills for free and easy to start | 一系列开源免费的金融分析Agent Skills
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
Toolkit for working with the DOTA aerial object detection dataset
A Python package for fast and robust Image Stitching
支持多张图片进行图像拼接 It can use more than two pictures to make a panorama.
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
[CVPR 2025] Complexity Experts are Task-Discriminative Learners for Any Image Restoration
Experiments with MoireDet from Doing More With Moiré Pattern Detection in Digital Photos