GitHub Repos intermediate 2 min read Apr 8, 2026 · Updated Apr 15, 2026
Public Preview Sign in free for the full digest →

Shopify CEO's side project for your local search in CLI

“19k developers just discovered what the CEO of Shopify builds on weekends — and it solves the one thing Obsidian can't do.”

Shopify CEO's side project for your local search in CLI
5 Views
0 Likes
0 Bookmarks
Source · github.com

“QMD is an implementation of the best practices that I picked up in meetings with teams that work in search and retrieval. I tried to make it not overkill and keep things local. — Tobias Lütke, HN comment Jan 2026”

You know that feeling when you have hundreds of markdown notes scattered across folders, and Obsidian's search finds exact keyword matches but completely misses the conceptual connection you're looking for? You remember writing something about authentication flows, but searching 'auth' returns 50 files and none of them are what you need. QMD gives you semantic search that understands 'how do users log in' should surface your OAuth implementation notes, even if those exact words never appear together.

clisearchlocal-firstmarkdownvector-searchllmmcp

Think of QMD like having three librarians working together: one who's great at finding exact keyword matches (BM25), one who understands the meaning behind your question (vector embeddings), and one who's a subject expert who double-checks the results (LLM reranking). You point it at your folders, it indexes everything into a local SQLite database, generates vector embeddings for each chunk of text, and when you search, it runs all three approaches in parallel then blends the results. The clever bit: it chunks code files at function and class boundaries using tree-sitter, so a 500-line Python file becomes searchable by individual functions, not as one giant blob.

01
Three search modes — you get fast keyword search (BM25), semantic understanding (vector), or hybrid with AI reranking for best results
02
AST-aware code chunking — your Python and TypeScript files get indexed by function and class boundaries, not arbitrary line breaks, so you find the right function, not just the right file
03
MCP server for AI agents — Claude, Cursor, or any MCP-compatible AI can search your docs directly, enabling agentic workflows without you manually copy-pasting context
04
Fine-tuned query expansion model — a custom 1.7B model trained with GRPO generates better search variations, not just a stock LLM
05
Entirely local with no cloud APIs — ~2GB of models download once, then everything runs offline with zero external dependencies or data leaving your machine
06
SDK library mode — you can embed QMD directly in your Node.js or Bun apps via `@tobilu/qmd`, not just use the CLI
Who it’s for

If you're a developer with hundreds of markdown notes in Obsidian, VS Code, or scattered across folders, and you've ever been frustrated that search only finds exact keyword matches — this is for you. Also valuable if you're building AI agents and need a local knowledge base they can query via MCP. Not for you if you need cloud sync, team collaboration, or a GUI — this is CLI-first, single-user, local-only.

Worth exploring

Yes, worth trying if you have a local markdown collection and want semantic search. The project is in active development (v2.1.0 released April 5, 2026 with 25+ community PRs), has clear momentum (19k stars in 4 months), and the architecture is well-documented. The main caveats: macOS requires Homebrew SQLite, Windows has reported CUDA issues (Issue #519), and there's no cloud API option — it's local-only by design. If you're on macOS or Linux with a GPU, it's a solid weekend experiment.

Developer playbook
Tech stack, code snippet, sentiment, alternatives.
PM playbook
Adoption angles, user fit, positioning.
CEO playbook
Traction signals, ROI, build vs buy.
Deep-dive insight
Full long-form analysis, no fluff.
Easy mode
Core idea, fast — when you need the gist.
Pro mode
Technical nuance, edge cases, tradeoffs.
Read the full digest
Go beyond the preview

Deep-dive insight, Easy and Pro modes, plus action playbooks — the full breakdown is one tap away.

Underrated tools. Unfiltered takes.

Read the full digest in the Snaplyze app for deep-dive insight, Easy and Pro modes, and the playbooks you can actually use.

Install Snaplyze →