Search local markdown and text collections with hybrid retrieval.
npx skills add https://github.com/Aevonix/colony-ai --skill qmd-aevonix
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/Aevonix/colony-ai/tree/main/optional-skills/research/qmd Command: npx skills add https://github.com/Aevonix/colony-ai --skill qmd-aevonix
## What problem does it solve? Local search of personal knowledge bases, notes, docs, and transcripts using a hybrid retrieval engine (BM25, vector search, and LLM reranking) on-device with no cloud dependency.
## Core Features & Use Cases
### Quick Start Index my notes directory and search for information on a given topic across all collections.
High-intent search queries and answers about installing and using this skill.
Offline markdown search uses a hybrid retrieval engine combining BM25, vector search, and LLM reranking to index notes and transcripts locally on-device, returning relevant results without any cloud dependency.
Hybrid retrieval for personal knowledge bases combines BM25 keyword matching, vector search, and LLM reranking to produce fast, relevant search results across local text collections without relying on cloud services.
Yes, local knowledge base search supports MCP integration and CLI usage, allowing seamless automation of on-device indexing and retrieval workflows within Colony environments.
On-device vector search works entirely offline by storing vectors locally and using configurable models, ensuring personal documentation and notes remain private without any cloud dependencies.
The best way to index personal documentation locally is using an on-device hybrid ranking system that applies BM25, vector search, and LLM reranking to deliver fast, relevant retrieval offline.
No, LLM reranking for notes operates on-device with configurable model usage and local vector storage, enabling offline search and retrieval of personal knowledge bases without an internet connection.
ChimeraFoundationaIndex local markdown notes, transcripts, and docs for hybrid on-device search.
MerkyorLynnSearch the web via Brave Search API and extract page content as Markdown.
overviewlabsSearch local Markdown collections with hybrid keyword and vector retrieval.
steipeteIndex local files and search them with BM25, vector, and hybrid queries.
