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 collection of system prompts, tool definitions, and behavioral configurations extracted from dozens of commercial and open-source AI coding assistants and products. It contains over 100 text files organized by vendor (Anthropic, Cursor, VSCode Agent, Manus, Devin, Replit, etc.), each representing a snapshot of how these AI agents are instructed to behave, what tools they can use, and what safety rules they follow. The collection is not an application or a data pipeline; it is a reference archive for researchers, prompt engineers, and developers studying AI agent design patterns, prompt injection risks, and competitive analysis. The repository includes both full system prompts (e.g., Claude Code 2.0, Cursor Agent, Manus) and structured tool JSON schemas that define function-calling APIs. While the content is valuable for understanding AI agent architecture, the repository itself has no executable code, no versioning of individual prompts, and no automated validation, making it a static snapshot rather than a living project.