ChatGH

D4Vinci / Scrapling

Scrapling is an adaptive web scraping framework that handles everything from single requests to full-scale crawls. Its parser automatically relocates elements when websites update, while built-in fetchers bypass anti-bot systems like Cloudflare Turnstile out of the box.

huggingface / skills

Hugging Face Skills provides standardized AI/ML task definitions for coding agents like Claude Code, Codex, Gemini CLI, and Cursor. Includes skills for dataset creation, model training, evaluation, and Hugging Face Hub operations.

abhigyanpatwari / GitNexus

GitNexus is a zero-server code intelligence engine that indexes any codebase into a knowledge graph. It provides CLI + MCP for AI agents and a browser-based visual explorer, enabling deep code analysis with dependency tracking, call chains, and impact analysis across 9 languages.

obra / superpowers

Superpowers is a complete software development workflow for coding agents, built on composable skills that enforce TDD, systematic planning, subagent-driven development, and code review. It transforms AI from a code generator into a disciplined engineering partner.

muratcankoylan / Agent-Skills-for-Context-Engineering

A comprehensive collection of Agent Skills for context engineering, teaching the art of managing LLM context windows to build production-grade AI agent systems. Covers multi-agent patterns, memory systems, tool design, and evaluation frameworks.

datawhalechina / hello-agents

Hello-Agents is an open-source systematic tutorial from Datawhale for learning AI agents from scratch. Covering theory to practice, it guides you through ReAct paradigms, low-code platforms, custom frameworks, memory systems, and multi-agent collaboration, transforming you from an LLM user to an agent system builder.

bytedance / deer-flow

DeerFlow is an open-source super agent harness by ByteDance that orchestrates sub-agents, memory, and sandboxes to perform complex tasks. Built on LangGraph, it features extensible skills, sandboxed execution, long-term memory, and supports multi-agent workflows for deep research, automation, and content generation.

VectifyAI / PageIndex

PageIndex is a vectorless, reasoning-based RAG system that builds hierarchical tree indexes from long documents, enabling LLMs to perform human-like, agentic retrieval without vector databases or chunking.

NevaMind-AI / memU

memU is a memory framework for 24/7 proactive AI agents. It continuously captures user intent, reduces LLM token costs, and organizes memory like a file system for instant access. Enables always-on, evolving agents that learn from conversations, documents, and multimodal inputs.