This repository is a hybrid collection centered around an n8n workflow search engine. The core application is a Python/FastAPI server that indexes and serves ~4,300 n8n workflow JSON files via a SQLite FTS5-backed API, with a static GitHub Pages frontend for browsing. The workflows directory contains a large collection of n8n automation templates covering hundreds of integrations (Slack, Telegram, GitHub, Airtable, etc.), most structured as simple trigger-to-action pipelines. Beyond the main search engine, the repo includes an AI-stack sub-project (Docker Compose for n8n + Agent Zero + ComfyUI), a medical education Next.js app (medcards-ai), Kubernetes/Helm deployment configs, and various utility scripts. The codebase is functional but largely boilerplate — the FastAPI server implements standard CRUD/search patterns with basic security (path traversal protection, rate limiting, CORS), while the workflow JSON files are community-contributed examples of varying complexity. The sub-projects (ai-stack, medcards-ai) appear aspirational rather than production-ready, with the medcards-ai being a well-documented but untested Next.js application.
Diffusion Toolkit is a WPF desktop application for organizing, searching, and browsing AI-generated images. It scans folders for images, extracts generation parameters (prompt, seed, model, CFG, workflow, etc.) from multiple formats (AUTOMATIC1111, ComfyUI, NovelAI, etc.), and stores them in a SQLite database for fast metadata search, filtering, and album management. The application provides a rich thumbnail grid, preview pane, folder/album/tag navigation, and supports videos, external applications integration, and auto‑updating via GitHub releases. Although it demonstrates a depth of domain knowledge and addresses a real need for AI artists, the codebase has notable architectural anti‑patterns (global static service locator, monolithic classes, raw SQL in migrations, large XAML files), is tied to Windows/WPF with no headless component, and uses a forked version of sqlite‑net. The code is actively maintained with frequent commits, but its reusability is limited by tight coupling and lack of an inversion of control container.
This repository is the central index and deployment configuration for the trace.moe anime scene search engine. It contains no application code; the actual functionality is implemented in separate repositories (trace.moe-api, trace.moe-www, etc.). The primary artifact is a Docker Compose file that orchestrates the entire stack, including PostgreSQL, Milvus vector database, and the API server. This repo is useful for operators who want to deploy the trace.moe system, but developers looking for reusable code should look at the sub-repositories. The documentation provides clear, step-by-step deployment instructions. The system itself is an image-based scene search service that uses vector similarity search to identify anime scenes from screenshots.