QMD is an open‑source, MIT‑licensed local search engine written in TypeScript that combines BM25, vector embeddings via a GGUF model, and an LLM reranker, allowing natural‑language queries over thousands of markdown files without network calls, and can be installed with just three commands.
This article walks through how to assemble a personal LLM‑driven wiki using Claude Code, Obsidian, and the open‑source qmd search engine, detailing the directory layout, CLAUDE.md workflow spec, ingestion/query/health‑check cycles, and how the approach can be extended for enterprise knowledge bases.
The article explains OpenClaw Memory's design—storing daily and permanent logs as Markdown files, managing them with Git, offering hybrid vector‑BM25 search, applying temporal decay to prioritize recent entries, and comparing SQLite and QMD backends with practical configuration examples and tips.
This article explains how to systematically organize experience evaluation using the QMD framework and PDCA cycle, covering goal definition, stakeholder roles, business selection, timeline planning, location setup, assessment methods, reliability checks, business review, reporting, and continuous improvement to ensure reliable, business‑aligned UX outcomes.
This article explains how 58 Tongcheng’s design team upgraded the QMD evaluation framework to QMD 3.0, using reliability testing, ICC analysis, and systematic process controls to make subjective UX scores more trustworthy and actionable across product lines.
This article explains how 58.com’s UX design team built and iterated the Quality Measure Driven (QMD) evaluation framework, aligning metrics with business value, customizing indicator composition and description, introducing weightings, and establishing a closed‑loop validation process to make experience assessment actionable across diverse product lines.
