qmd-cliSearch and retrieve markdown documents from local knowledge bases using qmd. Supports BM25 keyword search, vector semantic search, and hybrid search with LLM re-ranking. Use for querying indexed notes, documentation, meeting transcripts, and any markdown-based knowledge. Requires qmd CLI installed (bun install -g https://github.com/tobi/qmd).
Install via ClawdBot CLI:
clawdbot install dpaluy/qmd-cliSearch and retrieve documents from locally indexed markdown knowledge bases.
bun install -g https://github.com/tobi/qmd# Add a collection
qmd collection add ~/notes --name notes --mask "**/*.md"
# Generate embeddings (required for vsearch/query)
qmd embedAlways use --json flag for structured output when invoking qmd commands.
qmd search "authentication flow" --json
qmd search "error handling" --json -n 10
qmd search "config" --json -c notesqmd vsearch "how does login work" --json
qmd vsearch "authentication best practices" --json -n 20qmd query "implementing user auth" --json
qmd query "deployment process" --json --min-score 0.5| Option | Description |
|--------|-------------|
| -n NUM | Number of results (default: 5, or 20 with --json) |
| -c, --collection NAME | Restrict to specific collection |
| --min-score NUM | Minimum score threshold |
| --full | Return complete document content in results |
| --all | Return all matches |
qmd get docs/guide.md --json
qmd get "#a1b2c3" --json
qmd get notes/meeting.md:50 -l 100 --jsonqmd multi-get "docs/*.md" --json
qmd multi-get "api.md, guide.md, #abc123" --json
qmd multi-get "notes/**/*.md" --json --max-bytes 20480qmd update # Re-index changed files
qmd status # Check index health
qmd collection list # List all collections| Mode | Speed | Quality | Best For |
|------|-------|---------|----------|
| search | Fast | Good | Exact keywords, known terms |
| vsearch | Medium | Better | Conceptual queries, synonyms |
| query | Slow | Best | Complex questions, uncertain terms |
Performance note: vsearch and query have ~1 minute cold start latency for vector initialization. Prefer search for interactive use.
qmd can run as an MCP server for direct integration:
qmd mcpExposes tools: qmd_search, qmd_vsearch, qmd_query, qmd_get, qmd_multi_get, qmd_status
Generated Mar 1, 2026
Software development teams use qmd to quickly find relevant sections in extensive internal documentation, such as API guides or architecture decisions. The hybrid search with LLM re-ranking helps locate conceptual information when exact keywords are unknown, improving developer productivity during debugging or feature implementation.
Project managers index meeting notes and transcripts to retrieve past discussions on specific topics like project timelines or stakeholder feedback. The vector semantic search enables finding related conversations based on meaning, aiding in decision-making and ensuring continuity across meetings.
Researchers and students use qmd to search through personal markdown notes on literature reviews, experiments, or hypotheses. The BM25 keyword search allows fast lookup of known terms, while hybrid queries help connect disparate ideas across notes for synthesis and paper writing.
Support teams or HR departments utilize qmd to access indexed company policies, FAQs, or procedural guides. The ability to restrict searches to specific collections ensures relevant results, speeding up response times for employee inquiries and reducing reliance on manual searches.
Content creators and technical writers index markdown drafts and reference materials to find related content or avoid duplication. The multi-get command facilitates batch retrieval of documents for editing or consolidation, streamlining content production workflows.
Offer a free tier for individual users with basic search capabilities and limited collections, while charging teams or enterprises for advanced features like higher query limits, priority support, and enhanced LLM re-ranking. Revenue is generated through monthly subscriptions based on usage and number of users.
Sell licenses to organizations requiring data privacy and control, such as healthcare or finance, for self-hosted deployments of qmd with full customization. Revenue comes from one-time license fees or annual maintenance contracts, including updates and technical support for integration with existing systems.
Monetize by providing qmd as an API service or through the MCP server for seamless integration into third-party tools like chatbots or project management software. Revenue is generated via API call pricing tiers or custom development fees for tailored integrations, targeting developers and platform builders.
💬 Integration Tip
Integrate qmd via its MCP server to expose search tools directly in AI assistants or development environments, ensuring structured JSON output for easy parsing and automation in workflows.
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
Create, search, and manage Bear notes via grizzly CLI.
Track water and sleep with JSON file storage
Notion API for creating and managing pages, databases, and blocks.
Smart ClawdBot documentation access with local search index, cached snippets, and on-demand fetch. Token-efficient and freshness-aware.
Work with Obsidian vaults as a knowledge base. Features: fuzzy/phonetic search across all notes, auto-folder detection for new notes, create/read/edit notes with frontmatter, manage tags and wikilinks. Use when: querying knowledge base, saving notes/documents, editing existing notes by user instructions.