This repository is a curated, open-source catalog of AI agent design patterns. It functions primarily as a documentation website (built with Astro, deployed to Vercel) that indexes ~200+ patterns across categories like orchestration, memory, security, and tool use. Patterns follow a strict template with YAML frontmatter, evidence grading, and cross-references. The codebase includes a static site generator, automated research pipelines (arXiv scanning, similarity checking), and CI/CD for pattern validation. While the core deliverable is a web application, the repository also contains significant research infrastructure (scripts for paper discovery, reference verification, and pattern quality fixing), making it a hybrid between an application and a research data project. The source of truth is markdown files in `patterns/`; the build pipeline generates JSON, graph data, and site assets. The project is actively maintained with community contribution guidelines and automated PR review workflows.
This repository is a curated catalog of free design and development resources, structured entirely as a single large Markdown table in readme.md. It contains no executable code, no build pipeline, no tests, and no programmatic data processing. The 'data' is a hand-curated list of ~600 external URLs organized into 30+ categories (UI Graphics, Fonts, Colors, Icons, CSS Frameworks, React UI Libraries, etc.), each with a short description. The only non-trivial file is the README itself; the rest are standard repository scaffolding (MIT license, contribution guidelines, PR template, Prettier ignore config). There is no data ingestion, transformation, or validation pipeline. The catalog is maintained through community pull requests that add individual entries to the Markdown tables.