qmd-1-0-0Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.
Install via ClawdBot CLI:
clawdbot install instant-picture/qmd-1-0-0Install qmd (node):
Install qmd (node)Requires:
Use qmd to index local files and search them.
Indexing
qmd collection add /path --name docs --mask "*/.md"qmd updateqmd statusSearch
qmd search "query"qmd vsearch "query"qmd query "query"qmd get docs/path.md:10 -l 40Notes
OLLAMA_URL (default http://localhost:11434).~/.cache/qmd by default.qmd mcp.Generated Mar 1, 2026
Software development teams can use qmd to index and search internal documentation, code comments, and markdown files. This enables quick retrieval of relevant information during development or debugging, improving productivity and knowledge sharing.
Researchers and students can index academic papers, notes, and reports in markdown format for efficient literature review. The hybrid search capabilities help find relevant sources quickly, supporting research projects and thesis writing.
Writers and editors can use qmd to organize and search through drafts, articles, and notes stored locally. This aids in maintaining consistency, referencing previous work, and speeding up the content creation process.
IT departments can index troubleshooting guides, FAQs, and internal wikis to provide fast, accurate support responses. The search functionality helps support agents find solutions quickly, reducing resolution times.
Law firms and legal teams can index contracts, case files, and legal notes for rapid search and reference. This supports case preparation, compliance checks, and document review by enabling efficient information retrieval.
Offer qmd as a cloud-based service with enhanced features like team collaboration, advanced analytics, and API access. Charge monthly or annual subscriptions based on usage tiers, such as storage limits or number of users.
Sell on-premise or custom deployments of qmd to large organizations with strict data privacy requirements. Provide dedicated support, training, and integration services, generating revenue through one-time licenses and ongoing maintenance fees.
Provide a free version of qmd for individual users with basic search capabilities, while charging for advanced features like vector search, priority support, and integrations with other tools. Monetize through in-app purchases or tiered plans.
💬 Integration Tip
Ensure Ollama is running locally for embeddings and reranking, and configure the OLLAMA_URL environment variable if using a non-default setup. Use the MCP mode for integration with other tools via the Model Context Protocol.
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Clawdbot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.
Use when designing database schemas, writing migrations, optimizing SQL queries, fixing N+1 problems, creating indexes, setting up PostgreSQL, configuring EF Core, implementing caching, partitioning tables, or any database performance question.
Connect to Supabase for database operations, vector search, and storage. Use for storing data, running SQL queries, similarity search with pgvector, and managing tables. Triggers on requests involving databases, vector stores, embeddings, or Supabase specifically.
Query, design, migrate, and optimize SQL databases. Use when working with SQLite, PostgreSQL, or MySQL — schema design, writing queries, creating migrations, indexing, backup/restore, and debugging slow queries. No ORMs required.