AIくさい日本語を人間が書いた文章に変換するClaude Codeスキル。20パターンのチェックリスト+書き換えガイド。

TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML

「テストを書かない研究者に送る “最初にテストを書く” 実験コード入門 – オレオレ最強 main.py から抜け出すために –」 のサンプルコード

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

Cleaned Wikipedia paragraphs for natural language processing (NLP)

OpenReview論文を自動で発見・分析する日本語対応AIエージェント

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Convert PDF to markdown + JSON quickly with high accuracy

Training Sparse Autoencoders on Language Models

Measure prompt and skill improvements with blind A/B comparison.

Dr. Zero Self-Evolving Search Agents without Training Data

The memory harness for proactive AI agents — structured storage, intent capture, 10x token reduction.

🚀 The fast, Pythonic way to build MCP servers and clients.

This solution accelerator leverages Microsoft Foundry, Azure Content Understanding, Azure OpenAI Service, and Foundry IQ to enable organizations to derive insights from volumes of conversational da…

The Release Manager Assistant (RMA) is an AI-powered solution accelerator that enhances the software release process by integrating multiple systems and providing real-time decision support. Design…

EnterpriseBench is a comprehensive framework designed to evaluate Large Language Model (LLM) agents within realistic enterprise environments. It provides a complete ecosystem for generating, simula…

YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.

Build, run, and manage agent platforms.

Semantic Kernel (SK) is a lightweight SDK enabling integration of AI Large Language Models (LLMs) with conventional programming languages.

⚡Japanese sentence splitting(日本語文境界判定器), 40–250× faster via a Rust-accelerated Python library with near-perfect API compatibility with megagonlabs/bunkai.

Playwright MCP server

MCP server for Claude to access Outlook data via Microsoft Graph API

A Model Context Protocol (MCP) server that enables AI assistants to interact with AKS clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and AKS.

書籍『今日から使えるファインチューニングレシピ』のGitHubリポジトリです。

Sample on how to run a LLM using LM Studio and interact with the model using Semantic Kernel.