GitHub 2026-09-16 Weekly Trending Projects

Provides coding assistants an action-first, numbered ADHD-friendly output style to cut verbosity and clarify next steps for faster execution.

God's Eye View is a browser-based open-source spatial-intelligence platform that renders a photorealistic 3D globe populated with live public feeds—aircraft, ships, satellites, earthquakes and public cameras—plus voice-agent control, shader-driven sensor styles and shareable scenes. It targets OSINT practitioners, researchers and creators who need real-time geospatial visualization, but it depends on third-party map APIs, API keys and feed availability and currently shows limited community maintenance.

This repository assembles curated Codex plugin examples and cross‑platform reference implementations that use a unified manifest and companion surface structure; it serves as a practical reference for plugin development, integration, and teaching, but prospective adopters should verify license and maintenance details to mitigate adoption risk.

ECC adds planning, testing, review, and memory to coding agents like Claude Code as reusable tools.

A context-management server for MCP and LLM toolchains: it sandboxes outputs, indexes events with SQLite+FTS5 and retrieves via BM25, drastically cutting context usage while preserving session continuity—suitable for teams needing token-cost control and persistent conversation state.

An enterprise-oriented AI code-review CLI that pairs deterministic engineering with agents to improve precision and efficiency; suitable for CI integration but verify license and repo visibility first.

A minimization plugin for Claude Code and Codex that reuses native features without dropping safety checks.

Adds TDD, planning, and subagent review to coding agents instead of coding immediately.

Worktrunk manages Git worktrees for developers running Claude Code in parallel, replacing cumbersome path-based commands with wt.

Hyperframes renders deterministic videos from plain HTML, combining AI-agent-driven authoring and adapter-based animations to power automated content pipelines and repeatable video production.

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

A Markdown skill that removes AI-sounding prose with 35 patterns while preserving code and facts.

Provides a discoverable, installable catalog of agent skills for Codex to help teams package and reuse task capabilities; the repository currently lacks license information and active maintenance, so it is best evaluated and customized within controlled environments.

A pure-C inference engine for running 744B–2.8T MoE models locally, streaming experts from disk instead of fitting everything in VRAM.

A tool that converts natural-language descriptions into self-contained, theme-aware, high-resolution architecture and flow diagrams—well suited for rapid documentation and communication, but limited by an unclear license and minimal community activity.

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.

OpenMAIC uses multi-agent orchestration and pluggable models to rapidly turn topics or materials into interactive classrooms and teaching assets, suited for scalable course generation and rich-media export in educational scenarios.

An enterprise-grade RAG framework offering end-to-end document parsing, vector indexing and LLM inference—suited for private deployments and complex document retrieval scenarios.

A writing skill for ChatGPT, Claude Code, and Codex that removes AI clichés without standardizing your voice.

A modular CAD and robotics skills library for agents that converts natural-language or image requests into engineering outputs (STEP, STL, etc.), enabling local workflow and plugin integration for automated modeling and fabrication.

9Router is a local AI router with smart fallback and RTK compression to save 20–40% tokens, designed to give developers and teams uninterrupted, cost-efficient AI coding workflows across multiple providers.

Spec Kit uses executable specifications and a dedicated CLI to transform product intent into implementable tasks, ideal for teams relying on AI coding agents and spec-driven workflows; however, unclear contributor history and unknown license require assessment of compliance and maintenance risk before adoption.