gno
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs RAG/semantic search, or wants to start a local web UI for their docs.
Why use this skill?
Transform your local documents into a searchable AI knowledge base. GNO provides private, offline vector search and RAG for your files, notes, and code.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/gmickel/gnoWhat This Skill Does
GNO is a comprehensive local knowledge management and semantic search engine designed specifically for OpenClaw. It transforms scattered local files—such as PDFs, markdown notes, Word documents, and source code—into a searchable, intelligent vector-based knowledge base. By operating entirely offline, GNO ensures that your sensitive documents never leave your machine, providing high-speed indexing and retrieval without the need for external API keys or cloud dependencies. The skill supports advanced RAG (Retrieval-Augmented Generation), allowing the AI to answer complex questions based specifically on the content within your local directory. Beyond simple keyword matching, GNO leverages vector embeddings to find semantically relevant information, identifies document relationships via graph-based linking, and offers an intuitive web UI for visual data exploration.
Installation
To integrate GNO into your OpenClaw environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/gmickel/gno
Once installed, initialize the skill in your target directory by running gno init. You can then begin adding folders to your collection using gno collection add <path> --name <collection_name> and finalize the setup by executing gno index to build the searchable vector embeddings.
Use Cases
- Research & Academia: Index thousands of research papers and PDFs to perform semantic queries and find connections between disparate topics.
- Knowledge Management: Convert a directory of Obsidian or Notion markdown exports into an AI-queryable wiki with support for backlinks and graph visualization.
- Software Development: Search through complex, large-scale codebases where standard text-based grep falls short of understanding context and intent.
- Local Documentation Access: Maintain a private, high-speed searchable interface for technical manuals, local documentation, and personal notes.
Example Prompts
- "Search my project docs for any information regarding our current API authentication flow and summarize it for me."
- "Index the folder ~/Documents/Research and then find all documents related to climate change models and show me their connections in the graph view."
- "Based on my local notes in the 'project-alpha' collection, what are the primary blockers we identified last week?"
Tips & Limitations
- Indexing Performance: The time taken to index depends on your CPU and the volume of files; for very large directories, use the
updatecommand instead of a full re-index to save time. - Privacy First: GNO is designed for local-only operation. Avoid placing files in indexed directories that contain sensitive system-level configurations unless explicitly intended.
- Model Selection: The quality of RAG answers depends on the local model currently in use; ensure you have a high-quality model pulled via
gno models pullfor the best results. - Maintenance: Regularly run
gno doctorif you notice search results are inconsistent, as this will help identify corrupted index segments.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-gmickel-gno": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write