Explore the directory

A collection of Agent Skills and Claude Code plugins that teach coding agents Terraform and Packer, organized into installable product plugin bundles.

• Agent skills

A Swift library for running large language models locally on macOS, iOS, watchOS, tvOS and visionOS, built around llama.cpp with automatic chat-template handling from a model's GGUF metadata.

• Inference
• Libraries

An agent skill that makes coding agents regenerate commit messages, pull request titles, and other delivery text from the final, adopted state of the work, instead of carrying forward rejected drafts or intermediate discussion.

• Agent skills

A Claude Code plugin marketplace that packages a skill teaching an agent to use ast-grep's abstract-syntax-tree pattern matching for structural code search instead of plain text search.

• Agent skills
• Code quality

A tool for generating synthetic training data for language models and agent evaluations, combining reasoning traces with tool-calling patterns through topic-graph-guided sample generation.

• Models
• AI evals

A language server that connects code editors to LLMs for code completion, handling prompt construction, context-window tokenization and multi-backend model access so editor extensions can stay lightweight.

• Inference
• Editors

A collection of sample prompts, agent instructions and reusable Skill files for Microsoft 365 Copilot, GitHub Copilot and Microsoft Copilot, contributed by Microsoft product teams and the community.

• Agent skills

A concise, categorized list of Model Context Protocol servers, covering browser and mobile control, cloud platforms, databases, developer tools and more.

• MCP servers
• Curated lists

An Unreal Engine 5.7 editor plugin that embeds the Claude Code CLI in a docked chat panel and runs an MCP server exposing actor, Blueprint, level and asset editing tools.

• Coding agents
• MCP servers

A vision toolkit and skill that gives text-only models running in DeepSeek Harness image understanding: pasted-image Q&A, long-screenshot OCR, UI restoration and pixel-level comparison.

• Agent skills

An experimental Python translation of Microsoft's TypeAgent KnowPro project, aimed at structured retrieval-augmented generation: ingesting, indexing and querying data through an LLM.

• RAG

An MCP server that gives an AI agent access to the entire Cloudflare API by generating and running short pieces of code against it, instead of registering thousands of individual tools.

• MCP servers

An engineering pipeline that turns AI-assisted coding into a nine-stage, gated workflow, from requirement through design, development, test and review, usable identically across several coding agents.

• Coding agents
• Agent skills

A collection of Jupyter notebooks demonstrating how to apply generative AI agent frameworks such as AutoGen, LlamaIndex and CrewAI to financial analysis, trading strategy and RAG on earnings reports.

• Tutorials

A local inference engine for Apple silicon that runs coding agents and OpenAI or Anthropic compatible applications on one Mac, combining speculative decoding with Metal kernels and automatic memory planning.

• Inference

A graph database that combines Neo4j-compatible Bolt and Cypher access with vector search and MVCC-based historical reads, aimed at agent memory, graph-RAG and audit-friendly knowledge stores.

• Agent memory
• Databases

A network scanning and vulnerability assessment tool for wired and Wi-Fi networks, running on a Raspberry Pi or a headless server, with a web dashboard for discovery, threat intelligence, and offensive-security testing.

• Security
• Networking

A collection of Chinese-language notes on LLM inference, transformer model structure and framework internals, covering quantization, attention optimizations, CUDA and Triton kernel programming.

• Books

A self-improving QA test harness that runs natural-language test scripts for web and mobile apps, re-observing the interface to recover from failed steps and building memory across runs to catch regressions.

• Testing

An agent operating system for building and running private agentic AI applications, with agent creation, a knowledge base, a model proxy, a memory system and a plugin ecosystem, deployed locally with Docker.

• Agent frameworks

A Chinese-language tutorial series covering environment setup on macOS and Windows, coding-agent CLIs, MCP, Skills and multi-agent workflow governance for AI-assisted coding.

• Tutorials

A collection of plugins that equip AI coding agents such as Claude Code, Codex and Cursor with skills, MCP servers and hooks for architecting, deploying and operating AWS infrastructure.

• Agent skills
• Hosting

A proxy written in Go that lets a local Ollama model, or DeepSeek and Mistral, act as a GitHub Copilot style code completion backend for editors such as Neovim, VS Code and Zed.

• Inference
• Editors

A serving framework for audio and multimodal AI models that runs text-to-speech, speech recognition, and omni chat models behind an OpenAI-compatible API, built to handle multi-stage generation pipelines.

• Inference
• Speech