qmd-externalLocal hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.
Install via ClawdBot CLI:
clawdbot install levineam/qmd-externalInstall qmd via Bun:
Install qmd via BunRequires:
Local search engine for Markdown notes, docs, and knowledge bases. Index once, search fast.
qmd search (BM25). It's typically instant and should be the default.qmd vsearch only when keyword search fails and you need semantic similarity (can be very slow on a cold start).qmd query unless the user explicitly wants the highest quality hybrid results and can tolerate long runtimes/timeouts.brew install sqlite (SQLite extensions)$HOME/.bun/binInstall Bun (macOS): brew install oven-sh/bun/bun
bun install -g https://github.com/tobi/qmd
qmd collection add /path/to/notes --name notes --mask "**/*.md"
qmd context add qmd://notes "Description of this collection" # optional
qmd embed # one-time to enable vector + hybrid search*/.md).qmd search (default): fast keyword match (BM25)qmd vsearch (last resort): semantic similarity (vector). Often slow due to local LLM work before the vector lookup.qmd query (generally skip): hybrid search + LLM reranking. Often slower than vsearch and may timeout.qmd search is typically instant.qmd vsearch can be ~1 minute on some machines because query expansion may load a local model (e.g., Qwen3-1.7B) into memory per run; the vector lookup itself is usually fast.qmd query adds LLM reranking on top of vsearch, so it can be even slower and less reliable for interactive use.qmd search "query" # default
qmd vsearch "query"
qmd query "query"
qmd search "query" -c notes # Search specific collection
qmd search "query" -n 10 # More results
qmd search "query" --json # JSON output
qmd search "query" --all --files --min-score 0.3-n : number of results-c, --collection : restrict to a collection--all --min-score : return all matches above a threshold--json / --files: agent-friendly output formats--full: return full document contentqmd get "path/to/file.md" # Full document
qmd get "#docid" # By ID from search results
qmd multi-get "journals/2025-05*.md"
qmd multi-get "doc1.md, doc2.md, #abc123" --jsonqmd status # Index health
qmd update # Re-index changed files
qmd embed # Update embeddingsSet up a cron job or hook to automatically re-index. For example, a daily 5 AM reindex:
# Via Clawdbot cron (isolated job, runs silently):
clawdbot cron add \
--name "qmd-reindex" \
--cron "0 5 * * *" \
--tz "America/New_York" \
--session isolated \
--message "Run: export PATH=\"\$HOME/.bun/bin:\$PATH\" && qmd update && qmd embed"
# Or via system crontab:
0 5 * * * export PATH="$HOME/.bun/bin:$PATH" && qmd update && qmd embedThis ensures your vault search stays current as you add or edit notes.
~/.cache/qmd/models/ (override with XDG_CACHE_HOME).qmd searches your local files (notes/docs) that you explicitly index into collections.memory_search searches agent memory (saved facts/context from prior interactions).memory_search for "what did we decide/learn before?", qmd for "what's in my notes/docs on disk?".Generated Mar 1, 2026
Researchers can index their markdown notes, literature summaries, and project documentation. They use fast keyword search to quickly find relevant notes during writing or analysis, and semantic search to discover connections between disparate research ideas.
Development teams index internal markdown documentation, API guides, and architecture notes. Engineers use instant keyword search to retrieve specific technical details while coding, avoiding context-switching to external tools.
Writers, bloggers, and podcasters index their markdown notes, drafts, and reference materials. They rely on fast searches to pull up past ideas or related content during content creation, enhancing productivity and consistency.
Legal professionals index markdown files containing case notes, regulations, and compliance guidelines. They use keyword search to quickly access specific legal precedents or rules during case preparation or audits.
Offer a free tier for individual users with basic search features, and charge teams for advanced capabilities like collaborative indexing, priority support, and integration with cloud storage. Revenue comes from monthly subscriptions based on user count and storage.
Sell licenses for on-premises deployment to large organizations needing data privacy and custom integrations. Provide setup support, maintenance services, and training. Revenue is generated through one-time license fees and annual support contracts.
Offer consulting services to help businesses integrate qmd into their existing workflows, such as setting up automated indexing pipelines or developing plugins for specific tools. Revenue comes from project-based fees and ongoing retainer agreements.
💬 Integration Tip
Set up a cron job to automatically re-index markdown files daily, ensuring search results stay current without manual intervention.
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.