qmdLocal search/indexing CLI (BM25 + vectors + rerank) with MCP mode.
Install via ClawdBot CLI:
clawdbot install steipete/qmdInstall 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 Feb 26, 2026
Software developers can index and search their local documentation, code comments, and README files to quickly find relevant information while coding. This reduces context switching and improves productivity by enabling fast retrieval of technical details without leaving the terminal.
Researchers and students can index academic papers, notes, and markdown files stored locally to perform hybrid searches combining keyword and semantic queries. This helps in literature reviews by efficiently locating relevant sources and insights across a personal knowledge base.
Writers and content creators can organize and search through drafts, articles, and markdown notes to retrieve ideas or references quickly. The hybrid search capability allows finding content by both specific terms and contextual meaning, streamlining the writing process.
Small teams or startups can use this tool to create a lightweight, local search index for internal documents, meeting notes, and project files. It enables team members to find information without relying on cloud services, enhancing data privacy and reducing dependency on external tools.
Offer the core CLI tool for free to attract individual users and small teams, then charge for advanced features like cloud sync, team collaboration, or premium support. Revenue can come from subscriptions or one-time licenses for enterprise versions with enhanced capabilities.
Provide paid consulting services to help organizations integrate this tool into their workflows, such as setting up custom indexing pipelines or developing plugins. This targets businesses needing tailored solutions for local search and knowledge management.
Maintain the tool as open source to build a community and gather contributions, while generating revenue through sponsorships, donations, or grants from companies that benefit from its use. This model fosters adoption and continuous improvement through community feedback.
💬 Integration Tip
Set the OLLAMA_URL environment variable to use embeddings and reranking features, and ensure the qmd binary is installed and accessible in the system PATH for seamless CLI usage.
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.
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.
Design data models for construction projects. Create entity-relationship diagrams, define schemas, and generate database structures.