Search

An AI coding protocol that stops vibecoding slop and forces you to write your own core logic.

A robust, local desktop integration toolkit providing a secure sandbox for developing and testing AI model interactions.

A Python abstraction layer that makes Redis or DragonflyDB behave like a shared Python object across processes/microservices.

The teal gradient dies here

Reusable Agent Skills for embedded systems, MCU debugging, firmware workflows, and AI automation. （嵌入式、MCU 调试、固件流程与 AI 自动化的可复用 Agent Skills 集合）。

Full-stack Next.js development plugin for Claude Code

Skill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step model enforcement, 30%+ savings on multi-step chains.

Open registry of community-contributed AI coding skills (SKILL.md files) — daily-synced to skills-hub.ai. Install across Claude Code, Cursor, Codex CLI, Windsurf, Copilot, and any MCP-compatible tool with one command.

Frontend coding conventions for AI coding agents (Claude Code, Cursor, Codex). 67 rules for Next.js 16 + React 19 + TanStack Query v5 + FSD.

Run LLMs locally. One command.

A high-performance static internet index for LLM RAG applications

Automate arXiv paper tracking with LLM-powered metadata extraction and Google Sheets sync.

Surgical Activation Sparsity for LLMs on Blackwell Architectures

Aevum — LiteLLM-backed LLM complication with episodic ledger record.

Add your description here

A simple library to interact with various LLM providers

AI coding assistant skills for Claude Code, Gemini CLI, and Codex CLI

Ghost Admin API CLI tool

LLM tool definitions and execution-plan resolver for DG-Lab Coyote control

Contextual Memory and Prompt Optimization Toolkit for LLM-powered development