GitHub 2026-05-22 Daily Trending Projects

Anthropic-maintained Claude Code plugin directory offering standardized plugin structure and easy installation; useful for developers and operators, but third-party plugins require careful security and license review.

CodeGraph provides a local semantic index and graph traversal layer for Claude Code, dramatically reducing file scanning and tool calls—ideal for privacy-minded teams and large/multi-language codebases to accelerate code exploration and impact analysis.

Provides teams using Claude Code or general LLM coding agents with a compact, verifiable set of four guidelines and integration options to reduce assumptions, prevent overengineering, and limit edit scope to lower regression risk.

dotnet/skills is a .NET team–curated collection of agent-oriented skills and plugins covering build diagnostics, data access, testing, upgrades, MAUI and more for reuse in clients like Copilot and Cursor; however, current repository contributor and licensing information is lacking, so validate maintenance activity and compliance before adoption.

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.

Makes software agent-accessible via a CLI ecosystem with a central Hub, skill registry, and multi-source installers for automation and agent orchestration

OpenWA is an open-source WhatsApp API gateway for developers, emphasizing pluggable backends and multi-session management — suitable for teams building a self-hosted messaging platform, but verify license and maintenance status before production use to mitigate compliance and operational risk.

Chrome DevTools MCP exposes Chrome DevTools to AI coding agents via an MCP server, enabling automated browser control, deep debugging and performance analysis; however, the repository lacks contributors, commits, and releases, so evaluate maintenance and compliance risks before production use.

A hands-on, end-to-end AI engineering curriculum for programmers and engineers that spans math to multi-agent production; it stresses building algorithms from first principles and ships reusable artifacts each lesson to bridge theory and production.

notebooklm-py delivers full programmatic access to Google NotebookLM via async Python API and CLI for research and prototyping; it depends on undocumented APIs and has unclear licensing, so avoid production use.

An IDE-grade local coding agent that provides LSP/DAP coupling, a rich toolchain and subagent collaboration—well suited for large codebases needing precise edits, debugging, and automated code review.

Forge delivers a reliability infrastructure for self-hosted LLMs focused on tool-calling: combining guardrails middleware, an OpenAI-compatible proxy, and context compaction to markedly improve usability and stability of ~8B models on multi-step, tool-heavy tasks — suitable for teams requiring local inference and strong privacy control.

Multica delivers a self-hosted or cloud-managed platform to turn coding agents into assignable, monitored teammates with reusable skills—aimed at engineering teams seeking controlled automation.

Multi-agent AI toolkit for academic writing covering search, verification, drafting and review; emphasizes human-in-the-loop and quality gates

A curated, practical reference of tools, one-liners and cheatsheets for sysadmins, network engineers and security researchers — optimized for quick lookup and personal/operational reference; verify licenses and maintenance status before production use.

Streambert is an Electron-based cross-platform desktop app offering ad-free streaming, multithreaded downloads, subtitle management and anime-specific metadata integrations; suited for privacy-conscious power users who accept the legal and maintenance risks related to third-party sources.

Persona-centric AI agent collection with production-ready Claude Code templates for rapid specialist assistants; license and maintenance transparency are lacking.

S-UI is a Sing-Box based visual proxy management panel focused on multi-protocol support, subscription aggregation, and routing visualization—suitable for self-hosters and operators with debugging skills for testing and operations.

Understand-Anything is a plugin-based tool that converts codebases and knowledge bases into interactive knowledge graphs using multi-agent LLM extraction; it offers a visual dashboard, semantic search and diff impact analysis—suited for engineering and product teams needing fast onboarding and systemic understanding.