GitHub 2026-02-26 Daily Trending Projects

Scrapling is an adaptive web-scraping framework for the modern web, combining stealthy fetchers, multi-session concurrent crawls, and adaptive element tracking to build resumable, real-time, high-performance crawling workflows.

Hugging Face Skills delivers reusable skill bundles standardized via SKILL.md, compatible with multiple coding agents and shipped with manifests and examples—useful for delegating Hub operations and training/evaluation workflows to agents—while license clarity and community activity require verification.

GitNexus indexes codebases into a knowledge graph and exposes full dependency and call-chain views to AI agents, enabling precise impact analysis and safer automated refactoring for development teams.

Superpowers provides a composable skills library and TDD-enforced agent workflow for Claude Code, enabling end-to-end automation from design and planning to subagent execution, with plugin integration and extensibility.

This project offers a portable collection of context-engineering skills and practical patterns, emphasizing platform-agnostic design and progressive loading for building efficient, evaluable production-grade agent systems; however, license and maintenance uncertainties should be considered.

Hello‑Agents is a free open‑source, hands‑on tutorial that guides developers from fundamentals to implementation to build AI‑native agents and multi‑agent systems—covering frameworks, RAG, memory, Agentic‑RL and practical cases; best suited for practitioners with basic Python and LLM knowledge.

Extensible super-agent runtime with skills, sandbox execution and memory.

PageIndex converts long documents into semantic trees and uses LLM-driven tree search for reasoning-based retrieval, delivering vector-free, high-precision, and explainable retrieval for professional domains like finance and law.

MemU provides hierarchical, traceable multimodal memory management for LLMs and AI agents, supporting both RAG and LLM retrieval—suitable for rapid prototyping and enterprise self-hosting.

RuVector combines vector search, graph queries and local LLMs with self-learning indexes and single-file cognitive containers, targeting on‑prem, offline and edge deployments where data control and fast boot are priorities.

GPU-optimized library for large-scale Transformer training with modular building blocks and checkpoint interoperability.

A progressive, hands-on tutorial repository for developers and researchers that demonstrates how to build Claude-like AI coding agents across five increasing-complexity examples, emphasizing clear concepts and runnable samples.

An open collection of system prompts and models for prompt engineering and AI integration, covering many agents and developer tools—useful for experimentation and reuse, but requires review of GPL licensing and compliance risks before commercial adoption.

Plano elevates agent routing, model management, auditing, and observability into a standalone dataplane to reduce repeated engineering, enabling faster delivery and iteration in multi-model, multi-agent environments.

liyupi/ai-guide is a free, structured knowledge base and Vibe Coding tutorial set that consolidates models, tool reviews and hands-on projects to help beginners and developers quickly learn and ship AI-powered products.

A cross‑platform visual CLI management tool for Claude Code, Cursor and Codex users—aggregating sessions, offering real‑time chat, file and Git editing, plus optional AI task integration—suitable for developers and small teams needing a unified mobile/desktop workflow.