QMD - Query Markup Documents

An on-device search engine for everything you need to remember. Index your markdown notes, meeting transcripts, documentation, and knowledge bases. Search with keywords or natural language. Ideal for your agentic flows.

QMD combines BM25 full-text search, vector semantic search, and LLM re-ranking—all running locally via node-llama-cpp with GGUF models.

You can read more about QMD's progress in the CHANGELOG.

Quick Start

# Install globally (Node or Bun)
npm install -g @tobilu/qmd
# or
bun install -g @tobilu/qmd

# Or run directly
npx @tobilu/qmd ...
bunx @tobilu/qmd ...

# Create collections for your notes, docs, and meeting transcripts
qmd collection add ~/notes --name notes
qmd collection add ~/Documents/meetings --name meetings
qmd collection add ~/work/docs --name docs

# Add context to help with search results, each piece of context will be returned when matching sub documents are returned. This works as a tree. This is the key feature of QMD as it allows LLMs to make much better contextual choices when selecting documents. Don't sleep on it!
qmd context add qmd://notes "Personal notes and ideas"
qmd context add qmd://meetings "Meeting transcripts and notes"
qmd context add qmd://docs "Work documentation"

# Generate embeddings for semantic search
qmd embed

# Search across everything
qmd search "project timeline"           # Fast keyword search
qmd vsearch "how to deploy"             # Semantic search
qmd query "quarterly planning process"  # Hybrid + reranking (best quality)

# Get a specific document
qmd get "meetings/2024-01-15.md"

# Get a document by docid (shown in search results)
qmd get "#abc123"

# Get multiple documents by glob pattern
qmd multi-get "journals/2025-05*.md"

# Search within a specific collection
qmd search "API" -c notes

# Export all matches for an agent
qmd search "API" --all --files --min-score 0.3

Using with AI Agents

QMD's --json and --files output formats are designed for agentic workflows:

# Get structured results for an LLM
qmd search "authentication" --json -n 10

# List all relevant files above a threshold
qmd query "error handling" --all --files --min-score 0.4

# Retrieve full document content
qmd get "docs/api-reference.md" --full

MCP Server

Although the tool works perfectly fine when you just tell your agent to use it on the command line, it also exposes an MCP (Model Context Protocol) server for tighter integration.

Tools exposed:

• qmd_search - Fast BM25 keyword search (supports collection filter)
• qmd_vector_search - Semantic vector search (supports collection filter)
• qmd_deep_search - Deep search with query expansion and reranking (supports collection filter)
• qmd_get - Retrieve document by path or docid (with fuzzy matching suggestions)
• qmd_multi_get - Retrieve multiple documents by glob pattern, list, or docids
• qmd_status - Index health and collection info

Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "qmd": {
      "command": "qmd",
      "args": ["mcp"]
    }
  }
}

Claude Code — Install the plugin (recommended):

claude marketplace add tobi/qmd
claude plugin add qmd@qmd

Or configure MCP manually in ~/.claude/settings.json:

{
  "mcpServers": {
    "qmd": {
      "command": "qmd",
      "args": ["mcp"]
    }
  }
}

HTTP Transport

By default, QMD's MCP server uses stdio (launched as a subprocess by each client). For a shared, long-lived server that avoids repeated model loading, use the HTTP transport:

# Foreground (Ctrl-C to stop)
qmd mcp --http                    # localhost:8181
qmd mcp --http --port 8080        # custom port

# Background daemon
qmd mcp --http --daemon           # start, writes PID to ~/.cache/qmd/mcp.pid
qmd mcp stop                      # stop via PID file
qmd status                        # shows "MCP: running (PID ...)" when active

The HTTP server exposes two endpoints:

• POST /mcp — MCP Streamable HTTP (JSON responses, stateless)
• GET /health — liveness check with uptime

LLM models stay loaded in VRAM across requests. Embedding/reranking contexts are disposed after 5 min idle and transparently recreated on the next request (~1s penalty, models remain loaded).

Point any MCP client at http://localhost:8181/mcp to connect.

Architecture

┌─────────────────────────────────────────────────────────────────────────────┐
│                         QMD Hybrid Search Pipeline                          │
└─────────────────────────────────────────────────────────────────────────────┘

                              ┌─────────────────┐
                              │   User Query    │
                              └────────┬────────┘
                                       │
                        ┌──────────────┴──────────────┐
                        ▼                             ▼
               ┌────────────────┐            ┌────────────────┐
               │ Query Expansion│            │  Original Query│
               │  (fine-tuned)  │            │   (×2 weight)  │
               └───────┬────────┘            └───────┬────────┘
                       │                             │
                       │ 2 alternative queries       │
                       └──────────────┬──────────────┘
                                      │
              ┌───────────────────────┼───────────────────────┐
              ▼                       ▼                       ▼
     ┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
     │ Original Query  │     │ Expanded Query 1│     │ Expanded Query 2│
     └────────┬────────┘     └────────┬────────┘     └────────┬────────┘
              │                       │                       │
      ┌───────┴───────┐       ┌───────┴───────┐       ┌───────┴───────┐
      ▼               ▼       ▼               ▼       ▼               ▼
  ┌───────┐       ┌───────┐ ┌───────┐     ┌───────┐ ┌───────┐     ┌───────┐
  │ BM25  │       │Vector │ │ BM25  │     │Vector │ │ BM25  │     │Vector │
  │(FTS5) │       │Search │ │(FTS5) │     │Search │ │(FTS5) │     │Search │
  └───┬───┘       └───┬───┘ └───┬───┘     └───┬───┘ └───┬───┘     └───┬───┘
      │               │         │             │         │             │
      └───────┬───────┘         └──────┬──────┘         └──────┬──────┘
              │                        │                       │
              └────────────────────────┼───────────────────────┘
                                       │
                                       ▼
                          ┌───────────────────────┐
                          │   RRF Fusion + Bonus  │
                          │  Original query: ×2   │
                          │  Top-rank bonus: +0.05│
                          │     Top 30 Kept       │
                          └───────────┬───────────┘
                                      │
                                      ▼
                          ┌───────────────────────┐
                          │    LLM Re-ranking     │
                          │  (qwen3-reranker)     │
                          │  Yes/No + logprobs    │
                          └───────────┬───────────┘
                                      │
                                      ▼
                          ┌───────────────────────┐
                          │  Position-Aware Blend │
                          │  Top 1-3:  75% RRF    │
                          │  Top 4-10: 60% RRF    │
                          │  Top 11+:  40% RRF    │
                          └───────────────────────┘

Score Normalization & Fusion

Search Backends

Fusion Strategy

The query command uses Reciprocal Rank Fusion (RRF) with position-aware blending:

1. Query Expansion: Original query (×2 for weighting) + 1 LLM variation
2. Parallel Retrieval: Each query searches both FTS and vector indexes
3. RRF Fusion: Combine all result lists using score = Σ(1/(k+rank+1)) where k=60
4. Top-Rank Bonus: Documents ranking #1 in any list get +0.05, #2-3 get +0.02
5. Top-K Selection: Take top 30 candidates for reranking
6. Re-ranking: LLM scores each document (yes/no with logprobs confidence)
7. Position-Aware Blending:
   • RRF rank 1-3: 75% retrieval, 25% reranker (preserves exact matches)
   • RRF rank 4-10: 60% retrieval, 40% reranker
   • RRF rank 11+: 40% retrieval, 60% reranker (trust reranker more)

Why this approach: Pure RRF can dilute exact matches when expanded queries don't match. The top-rank bonus preserves documents that score #1 for the original query. Position-aware blending prevents the reranker from destroying high-confidence retrieval results.

Score Interpretation

Requirements

System Requirements

• Node.js >= 22
• Bun >= 1.0.0
• macOS: Homebrew SQLite (for extension support)

  brew install sqlite

GGUF Models (via node-llama-cpp)

QMD uses three local GGUF models (auto-downloaded on first use):

Models are downloaded from HuggingFace and cached in ~/.cache/qmd/models/.

Installation

npm install -g @tobilu/qmd
# or
bun install -g @tobilu/qmd

Development

git clone https://github.com/tobi/qmd
cd qmd
npm install
npm link

Usage

Collection Management

# Create a collection from current directory
qmd collection add . --name myproject

# Create a collection with explicit path and custom glob mask
qmd collection add ~/Documents/notes --name notes --mask "**/*.md"

# List all collections
qmd collection list

# Remove a collection
qmd collection remove myproject

# Rename a collection
qmd collection rename myproject my-project

# List files in a collection
qmd ls notes
qmd ls notes/subfolder

Generate Vector Embeddings

# Embed all indexed documents (900 tokens/chunk, 15% overlap)
qmd embed

# Force re-embed everything
qmd embed -f

Context Management

Context adds descriptive metadata to collections and paths, helping search understand your content.

# Add context to a collection (using qmd:// virtual paths)
qmd context add qmd://notes "Personal notes and ideas"
qmd context add qmd://docs/api "API documentation"

# Add context from within a collection directory
cd ~/notes && qmd context add "Personal notes and ideas"
cd ~/notes/work && qmd context add "Work-related notes"

# Add global context (applies to all collections)
qmd context add / "Knowledge base for my projects"

# List all contexts
qmd context list

# Remove context
qmd context rm qmd://notes/old

Search Commands

┌──────────────────────────────────────────────────────────────────┐
│                        Search Modes                              │
├──────────┬───────────────────────────────────────────────────────┤
│ search   │ BM25 full-text search only                           │
│ vsearch  │ Vector semantic search only                          │
│ query    │ Hybrid: FTS + Vector + Query Expansion + Re-ranking  │
└──────────┴───────────────────────────────────────────────────────┘

# Full-text search (fast, keyword-based)
qmd search "authentication flow"

# Vector search (semantic similarity)
qmd vsearch "how to login"

# Hybrid search with re-ranking (best quality)
qmd query "user authentication"

Options

# Search options
-n <num>           # Number of results (default: 5, or 20 for --files/--json)
-c, --collection   # Restrict search to a specific collection
--all              # Return all matches (use with --min-score to filter)
--min-score <num>  # Minimum score threshold (default: 0)
--full             # Show full document content
--line-numbers     # Add line numbers to output
--index <name>     # Use named index

# Output formats (for search and multi-get)
--files            # Output: docid,score,filepath,context
--json             # JSON output with snippets
--csv              # CSV output
--md               # Markdown output
--xml              # XML output

# Get options
qmd get <file>[:line]  # Get document, optionally starting at line
-l <num>               # Maximum lines to return
--from <num>           # Start from line number

# Multi-get options
-l <num>           # Maximum lines per file
--max-bytes <num>  # Skip files larger than N bytes (default: 10KB)

Output Format

Default output is colorized CLI format (respects NO_COLOR env):

docs/guide.md:42 #a1b2c3
Title: Software Craftsmanship
Context: Work documentation
Score: 93%

This section covers the **craftsmanship** of building
quality software with attention to detail.
See also: engineering principles


notes/meeting.md:15 #d4e5f6
Title: Q4 Planning
Context: Personal notes and ideas
Score: 67%

Discussion about code quality and craftsmanship
in the development process.

• Path: Collection-relative path (e.g., docs/guide.md)
• Docid: Short hash identifier (e.g., #a1b2c3) - use with qmd get #a1b2c3
• Title: Extracted from document (first heading or filename)
• Context: Path context if configured via qmd context add
• Score: Color-coded (green >70%, yellow >40%, dim otherwise)
• Snippet: Context around match with query terms highlighted

Examples

# Get 10 results with minimum score 0.3
qmd query -n 10 --min-score 0.3 "API design patterns"

# Output as markdown for LLM context
qmd search --md --full "error handling"

# JSON output for scripting
qmd query --json "quarterly reports"

# Use separate index for different knowledge base
qmd --index work search "quarterly reports"

Index Maintenance

# Show index status and collections with contexts
qmd status

# Re-index all collections
qmd update

# Re-index with git pull first (for remote repos)
qmd update --pull

# Get document by filepath (with fuzzy matching suggestions)
qmd get notes/meeting.md

# Get document by docid (from search results)
qmd get "#abc123"

# Get document starting at line 50, max 100 lines
qmd get notes/meeting.md:50 -l 100

# Get multiple documents by glob pattern
qmd multi-get "journals/2025-05*.md"

# Get multiple documents by comma-separated list (supports docids)
qmd multi-get "doc1.md, doc2.md, #abc123"

# Limit multi-get to files under 20KB
qmd multi-get "docs/*.md" --max-bytes 20480

# Output multi-get as JSON for agent processing
qmd multi-get "docs/*.md" --json

# Clean up cache and orphaned data
qmd cleanup

Data Storage

Index stored in: ~/.cache/qmd/index.sqlite

Schema

collections     -- Indexed directories with name and glob patterns
path_contexts   -- Context descriptions by virtual path (qmd://...)
documents       -- Markdown content with metadata and docid (6-char hash)
documents_fts   -- FTS5 full-text index
content_vectors -- Embedding chunks (hash, seq, pos, 900 tokens each)
vectors_vec     -- sqlite-vec vector index (hash_seq key)
llm_cache       -- Cached LLM responses (query expansion, rerank scores)

Environment Variables

How It Works

Indexing Flow

Collection ──► Glob Pattern ──► Markdown Files ──► Parse Title ──► Hash Content
    │                                                   │              │
    │                                                   │              ▼
    │                                                   │         Generate docid
    │                                                   │         (6-char hash)
    │                                                   │              │
    └──────────────────────────────────────────────────►└──► Store in SQLite
                                                                       │
                                                                       ▼
                                                                  FTS5 Index

Embedding Flow

Documents are chunked into ~900-token pieces with 15% overlap using smart boundary detection:

Document ──► Smart Chunk (~900 tokens) ──► Format each chunk ──► node-llama-cpp ──► Store Vectors
                │                           "title | text"        embedBatch()
                │
                └─► Chunks stored with:
                    - hash: document hash
                    - seq: chunk sequence (0, 1, 2...)
                    - pos: character position in original

Smart Chunking

Instead of cutting at hard token boundaries, QMD uses a scoring algorithm to find natural markdown break points. This keeps semantic units (sections, paragraphs, code blocks) together.

Break Point Scores:

Algorithm:

1. Scan document for all break points with scores
2. When approaching the 900-token target, search a 200-token window before the cutoff
3. Score each break point: finalScore = baseScore × (1 - (distance/window)² × 0.7)
4. Cut at the highest-scoring break point

The squared distance decay means a heading 200 tokens back (score ~30) still beats a simple line break at the target (score 1), but a closer heading wins over a distant one.

Code Fence Protection: Break points inside code blocks are ignored—code stays together. If a code block exceeds the chunk size, it's kept whole when possible.

Query Flow (Hybrid)

Query ──► LLM Expansion ──► [Original, Variant 1, Variant 2]
                │
      ┌─────────┴─────────┐
      ▼                   ▼
   For each query:     FTS (BM25)
      │                   │
      ▼                   ▼
   Vector Search      Ranked List
      │
      ▼
   Ranked List
      │
      └─────────┬─────────┘
                ▼
         RRF Fusion (k=60)
         Original query ×2 weight
         Top-rank bonus: +0.05/#1, +0.02/#2-3
                │
                ▼
         Top 30 candidates
                │
                ▼
         LLM Re-ranking
         (yes/no + logprob confidence)
                │
                ▼
         Position-Aware Blend
         Rank 1-3:  75% RRF / 25% reranker
         Rank 4-10: 60% RRF / 40% reranker
         Rank 11+:  40% RRF / 60% reranker
                │
                ▼
         Final Results

Model Configuration

Models are configured in src/llm.ts as HuggingFace URIs:

const DEFAULT_EMBED_MODEL = "hf:ggml-org/embeddinggemma-300M-GGUF/embeddinggemma-300M-Q8_0.gguf";
const DEFAULT_RERANK_MODEL = "hf:ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF/qwen3-reranker-0.6b-q8_0.gguf";
const DEFAULT_GENERATE_MODEL = "hf:tobil/qmd-query-expansion-1.7B-gguf/qmd-query-expansion-1.7B-q4_k_m.gguf";

EmbeddingGemma Prompt Format

// For queries
"task: search result | query: {query}"

// For documents
"title: {title} | text: {content}"

Qwen3-Reranker

Uses node-llama-cpp's createRankingContext() and rankAndSort() API for cross-encoder reranking. Returns documents sorted by relevance score (0.0 - 1.0).

Qwen3 (Query Expansion)

Used for generating query variations via LlamaChatSession.

License

MIT