GitHub 2026-04-15 Monthly Trending Projects

Hermes Agent is a server-deployable autonomous AI agent offering a terminal-first interface, multi-platform messaging gateway, persistent memory and skills hub, sandboxed terminals, and scheduling—suitable for long-running, auditable, and extensible automation in engineering and operations.

An extensible collection of agent skills for product and engineering teams that automates PRDs, planning, issue breakdowns and TDD flows, enabling modular integration of agent capabilities into repositories.

Offline-first server with local AI, offline Wikipedia and education content.

MoneyPrinterV2 is an automation toolkit combining social bots, short-video publishing and affiliate promotion, intended for users with Python skills to deploy and customize.

OpenScreen is an Electron-based free open-source screen recorder and demo maker offering recording, zooms, annotations and multi-resolution export—well suited for product demos and tutorials; note system-audio compatibility issues and incomplete repository metadata.

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

Native HUD for Claude Code that visualizes context, tools and agents for terminal debugging.

Last30Days is a multi-source trend briefing tool that searches and scores signals from social platforms, news, and prediction markets over the last 30 days, then synthesizes cited narratives—designed for researchers, prompt engineers, and product teams tracking short-term trends.

AI Edge Gallery is an on-device offline generative-AI sandbox for mobile, supporting local Gemma 4 inference, model management, and multimodal interaction—suitable for privacy-sensitive development and performance evaluation.

Everything Claude Code delivers a production-grade toolchain for agent harness performance and governance—covering skills, hooks, memory persistence, and security scanning—suited for teams requiring cross-platform parity and measurable quality gates.

TradingAgents constructs a modular, configurable research pipeline of role-based LLM agents, supporting multi-provider models and simulated execution—suited for academic and R&D strategy validation but not investment advice.

Open SWE is an open-source asynchronous coding agent that uses LLMs to plan and implement repository-wide changes—from issue-triggered tasks to automated PRs—enabling teams to scale code maintenance and workflow automation.

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.

Condenses Andrej Karpathy's observations about LLM coding pitfalls into four installable CLAUDE.md principles—explicit assumptions, simplicity-first, surgical changes, and goal-driven execution—helping teams limit unnecessary edits and make LLM-driven changes verifiable.

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.

VibeVoice is Microsoft's open-source voice synthesis framework that combines low-frame-rate continuous speech tokenizers, an LLM, and diffusion generation to target long-form multi-speaker and low-latency realtime scenarios; suitable for research and prototyping but carrying compliance, licensing, and misuse risks.

MarkItDown converts varied documents into structured Markdown for LLM pipelines, enabling automated text workflows while requiring care with optional dependencies and plugin compatibility.