Retrieve relevant information from local knowledge bases using hybrid search.
npx skills add https://github.com/kaminocorp/hermes-alpha --skill qmd-kaminocorp
Please help me install this Agent Skill. Skill: qmd Source: https://github.com/kaminocorp/hermes-alpha/tree/main/hermes-agent/optional-skills/research/qmd Command: npx skills add https://github.com/kaminocorp/hermes-alpha --skill qmd-kaminocorp
Retrieve relevant information from local notes, docs, and transcripts without leaving your environment, enabling faster decisions and knowledge reuse.
Ask the Hermes Agent to search your local knowledge base for "security incident response playbook".
High-intent search queries and answers about installing and using this skill.
You can search local Markdown notes and transcripts using a hybrid retrieval engine integrated directly into Hermes Agent workflows via MCP, applying BM25, vector similarity, and LLM reranking for accurate results without leaving your environment.
Hybrid ranking for local knowledge search combines BM25 text matching, vector similarity, and LLM reranking to accurately retrieve information from indexed Markdown notes, documentation, and transcripts.
Yes, this local knowledge search supports both CLI and MCP integration, enabling you to query indexed Markdown notes, documentation, and code directly from Hermes Agent workflows.
Yes, you can index and retrieve information from local code, documentation, and transcripts using the hybrid retrieval engine, which applies vector similarity and BM25 to deliver accurate knowledge base results.
The best way to locate policy details in local meeting notes is using a hybrid local search engine that indexes transcripts and applies BM25, vector search, and LLM reranking to pinpoint exact relevant information.
Chris-Chai-MinjaeIndex local text files for hybrid keyword and semantic search.
eddieluengSearch local markdown and text collections with hybrid retrieval and reranking.
nelohenriqIndex local markdown notes and transcripts for hybrid on-device search via MCP.
Yangel-hideSearch local knowledge stores with hybrid BM25, vector, and LLM reranking.
