Index local markdown notes and perform hybrid semantic search with BM25 and vector embeddings.
npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill qmd-cxnaive
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/cxnaive/hermes-agent-llbot/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/cxnaive/hermes-agent-llbot --skill qmd-cxnaive
This skill solves the challenge of fragmented personal knowledge by providing a unified, local search engine that indexes your notes, transcripts, and documentation without relying on cloud services.
Ask the agent to search your notes for a specific concept or document using the qmd query command.
High-intent search queries and answers about installing and using this skill.
Local semantic search over markdown notes and meeting transcripts is performed by indexing files on-device and combining BM25 keyword matching with vector embeddings and LLM reranking to retrieve precise results without cloud reliance.
Hybrid search for a personal knowledge base does not require an internet connection because the process operates entirely on-device using local GGUF models, ensuring notes and transcripts remain private and offline.
To set up on-device search for personal documentation, you need Node.js 22 and local GGUF model support to process and index markdown notes locally without external API dependencies.
You can use natural language queries to find specific decisions in past meeting transcripts because the hybrid search mechanism combines semantic vector search with LLM reranking to understand context and retrieve relevant information.
The best way to search across multiple project documentation folders locally is using a hybrid search approach that indexes local markdown files and applies BM25 alongside vector embeddings for high-precision information retrieval.
Indexing local markdown notes requires Node.js 22 to support the underlying on-device processing architecture and ensure compatibility with local GGUF model execution for semantic vector generation and LLM reranking.
JuanMS20Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.
opendatahub-ioExport vLLM CI Slack messages and convert them into markdown transcripts.
Yangel-hideSearch local knowledge stores with hybrid BM25, vector, and LLM reranking.
cdeistopenedIndex and search local Markdown collections with BM25 and vector embeddings.
