qmd vs Zindex

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.

Zindex is a diagram runtime built from the ground up for AI agents. Instead of generating one-shot diagram images, agents interact with Zindex through a Diagram Scene Protocol (DSP) — a structured set of 17 operations like add_node, update_edge, or apply_layout — and the platform validates the inputs, computes a proper layout using a Sugiyama-style hierarchical engine, and maintains a versioned, persistent diagram state that renders to SVG or PNG on demand. The pitch is that current diagram generation with tools like Mermaid or Graphviz is stateless and brittle: the agent generates a full diagram string, the renderer chokes on a syntax error, and you start over. Zindex makes diagrams a first-class collaborative artifact between agent and human — you can issue an operation, see the result, reject it, and the diagram rolls back. It supports architecture diagrams, BPMN flowcharts, ER diagrams, sequence diagrams, org charts, and network topology graphs, with 40+ built-in validation rules to catch invalid states before they ever render. Zindex is a SaaS product with an API-first design, though pricing has not been publicly disclosed. The project surfaced on Hacker News in April 2026, where the community was intrigued but skeptical — particularly around why this couldn't be done with structured Mermaid outputs, and whether the protocol overhead was justified for most agent use cases.