GitHub 2026-03-05 Monthly Trending Projects

Shannon is a white‑box autonomous AI pentester that, from source‑aware analysis, constructs and executes real exploit PoCs and produces reproducible reports—enabling security and development teams to move pentesting from a yearly event to a continuous process.

RuView: edge WiFi CSI pose/vital sensing on ESP32; fits rescue and research use, but requires CSI hardware and has unclear license/community.

OpenClaw is a local-first personal AI assistant that runs on your devices, offering multi-channel access, voice wake and a live Canvas — suited for privacy-focused users and developers seeking deep integrations.

Pi is a developer-focused monorepo toolkit offering a unified multi-provider LLM API, agent runtime, coding agent CLI, terminal and web UI components, and tools to manage vLLM GPU pods—suited for teams with TypeScript/Node skills building and deploying custom AI agents.

Claude‑skills supplies 66 specialized skills and 9 workflows for Claude‑based conversational programming, emphasizing context engineering and progressive disclosure—ideal for full‑stack teams using Claude as an expert pair programmer; however, there are no formal releases and contributor activity is low, so evaluate maintenance and compatibility risks before adoption.

GitHub Agentic Workflows enables natural-language Markdown definitions of AI agentic workflows run in GitHub Actions with layered guardrails for controlled repository automation; evaluate license, community maturity, and auditability before production deployment.

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.

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.

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.

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

QMD is a privacy-oriented on-device document retrieval tool that combines BM25 full-text, vector semantic search and LLM reranking — suited for individuals or teams needing offline, controllable search with structured outputs for agent workflows.

gogcli is a script- and terminal-focused CLI for Google services (Gmail/Calendar/Drive etc.), offering JSON-first output and multi-account management for automation use cases; however, missing license and maintenance data warrant cautious evaluation before production use.

SpacetimeDB lets you deploy application logic as Rust modules inside an in-memory-first relational database, targeting real-time multiplayer games and collaboration to achieve ultra-low latency and simplified single-binary operations.

A general-purpose sandbox platform for AI applications offering multi-language SDKs, unified APIs and Docker/Kubernetes runtimes to run agents, code execution and training workloads in isolated environments for debugging and evaluation.

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.

ClawHub provides a centralized registry for Clawdbot skills and 'souls' with versioning and vector search, enabling publish, discover and management of text-based agent skills—best suited for embedding-driven retrieval workflows.

CLI for solo devs and small teams: meta‑prompting and context engineering to enable spec‑driven builds with Claude/OpenCode for rapid prototyping.