GitHub 2026-11-03 Monthly Trending Projects

A local reverse-engineering tool connecting MCP agents to Hopper, Ghidra, and app runtime behavior, with evidence and limitations.

A coding-agent skill for security engineers that uses six phases and independent verification instead of one-shot scanning.

An end-to-end framework for web and mobile apps that drives them with natural language and replays recorded agent actions.

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.

Hallmark is an LLM design skill for Claude, Cursor, and Codex that generates self-contained HTML/CSS pages using macrostructures, 20 themes, and 57 quality gates—suited for teams needing portable design templates and controlled AI output; however, repository activity and compatibility should be evaluated before production use.

VoiceStudio is a local-first, multi-engine speech platform for cloning, dubbing and long-form audio production, aimed at teams prioritizing data privacy and self-hosted, high-throughput workflows.

Role-focused customizable plugins to integrate tools and codify workflows for Claude, improving team consistency.

A bili plugin for compressing long AI coding sessions: 100K windows can handle billions of tokens while summaries stay reversible and cache-friendly.

An SRE framework for security analysts to reverse-engineer multi-platform binaries interactively or automatically.

A memory plugin for Claude Code users that recalls session knowledge automatically with SQLite, Chroma, and lifecycle hooks.

Impeccable supplies an LLM-driven frontend design skillset—commands and references to audit, polish, and extract UI patterns—enabling teams to apply consistent design best practices across AI tools.

T3 Code is a minimal web GUI and cross-platform desktop for Codex/Claude coding agents, enabling quick validation of agent workflows; it is very early-stage with limited maintenance and contribution paths, suitable for exploratory trials and proof-of-concept.

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.

A Cursor pstack port for Claude Code and other agents, with poteto-mode routing and verification evidence.

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.

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.

FreeLLMAPI aggregates multiple free large‑model providers into a single self‑hosted OpenAI‑compatible proxy, offering automatic routing, per‑key rate tracking, and encrypted key storage; suitable for developers and teams who want to expand inference capacity at low cost while centralizing model access control.

Taste Skill supplies composable frontend 'skills' and an image-to-code pipeline that use adjustable design dials and GSAP scaffolds to accelerate turning AI outputs into implementations; however, missing license and contribution metadata require compliance and maintenance validation before production adoption.