All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine
- agent
- agent-skills
- asr
- fde
89,572 visible repositories in the index
721–744 of 1,267 · Most stars
All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine
AI coding agent skills for KiCad electronics design. Works with Claude Code and OpenAI Codex. Analyze schematics, review PCB layouts, EMC pre-compliance, SPICE simulation, download datasheets, source components, and prep boards for fabrication.
Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds
ARCH models in Python
微信SDK - 包括微信支付,微信公众号,微信登陆,微信消息处理等
jiant is an nlp toolkit
Machine learning with dataframes
Ouroboros — self-creating AI agent. Born Feb 16, 2026.
This tool will help manage tedious tasks in qBittorrent and automate them. Tag, categorize, remove Orphaned data, remove unregistered torrents and much much more.
Random proxy middleware for Scrapy
(2020-2022)The PyTorch version of SiamFC,SiamRPN,DaSiamRPN, UpdateNet , SiamDW, SiamRPN++, SiamMask, SiamFC++, SiamCAR, SiamBAN, Ocean, LightTrack , TrTr, NanoTrack; Visual object tracking based on deep learning
Python Library for PSLab Desktop: https://pslab.io
Write Processing sketches in Python
Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.
Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB / Octave
Hyper-parameter optimization for sklearn
看海量化回测平台 khQuant 开源版 V2.2:免费开源的 A 股量化回测桌面软件。不用开户、不用装 QMT,BaoStock / Tushare 下载数据到本地 DuckDB,Python 写策略,一键出回测报告。
🔮 An engineering framework to stop LLM hallucinations in Chinese astrology. / 给“赛博半仙”戴上紧箍咒:减少幻觉、固定排盘步骤的奇门遁甲与紫微斗数 AI skills。
Measuring Massive Multitask Language Understanding | ICLR 2021
TranslatedA Claude Code / Codex skill that makes AI create serious PPTX files
A backup-first Codex skill for keeping local Codex state fast, clean, and recoverable.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
Coding assistant MCP for Claude Desktop
High-quality implementations of standard and SOTA methods on a variety of tasks.