Starred repositories
Meta-Framework of Spatiotemporal Composability
将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
DeepSeek Harness: Everything is a Plugin.
Multi-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLI
Advanced Python Mastery (course by @dabeaz)
A free, source-available and fair-code licensed mac app cleaner
The best-benchmarked open-source AI memory system. And it's free.
A framework for building realtime voice AI agents 🤖🎙️📹
Clone any website with one command using AI coding agents
Simple, Pythonic remote execution and deployment.
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed…
The open-source alternative to Claude Cowork (powered by opencode)
A curated list of awesome libraries, packages, strategies, books, blogs, tutorials for systematic trading.
Multi-platform SDK for integrating GitHub Copilot Agent into apps and services
Native and Compact Structured Latents for 3D Generation
🎯 All you need. Nothing you don't. Open source project management that works for you, not against you.
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code…
12 Weeks, 24 Lessons, AI for All!
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Secure, Fast, and Extensible Sandbox runtime for AI agents.
Reorderable drag-and-drop lists for modern browsers and touch devices. No jQuery or framework required.
An evaluation and evolution tool for Agent Skills.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-rep…