Eden AI vs qmd

Eden AI is a European AI API gateway providing access to 500+ AI models behind a single unified interface. Unlike OpenRouter or similar US-based routers, Eden AI's entire infrastructure runs in the EU, offering GDPR compliance, EU data residency, and governance features aligned with the European AI Act — critical for industries like finance, healthcare, and government that can't route sensitive data through US-hosted intermediaries. The platform goes beyond just LLM routing: it also unifies computer vision, OCR, speech-to-text, translation, NLP, and document processing across multiple providers — making it the most complete multimodal AI gateway available. Smart routing, fallback handling, and cost optimization are built in, so teams can swap providers without rewriting integration code. Pay-as-you-go pricing with no mandatory subscription makes it accessible to small teams. Eden AI has re-emerged as a notable option in April 2026 as GDPR enforcement ramps up and European enterprises face increased scrutiny over where AI inference happens. With the US-EU data transfer framework still uncertain, a first-party European AI gateway with deep compliance tooling fills a real market gap that US-founded competitors can't easily address.

qmd is a lightweight local search engine built by Tobi Luetke, CEO of Shopify, for indexing and querying personal knowledge bases, documentation, and meeting notes — entirely offline. It combines three retrieval approaches in a single pipeline: BM25 full-text search for exact keyword matches, vector semantic search via ONNX-based embeddings, and LLM re-ranking using GGUF models through node-llama-cpp. All three stages run locally with no cloud dependency. The tool ships in multiple deployment modes: a CLI for ad-hoc queries, a Node.js library for programmatic use, an HTTP service for local API access, and — most useful for AI workflows — a native MCP server that lets Claude Code, Cursor, and similar editors query your local knowledge base directly during coding sessions. The hybrid retrieval approach means it handles both "find the exact error message from last week's standup notes" and "what was our decision about the auth architecture" equally well. What makes this notable beyond its technical approach is provenance: Luetke shipped it as a personal tool he actually uses, not a startup product. The GitHub history shows active iteration and he's been talking about it on X. It's a credible signal of where pragmatic AI-augmented knowledge management is heading for technical users who prefer local-first tools.