
qurio
by irahardianto·★ 16·Score 41
A self-hosted RAG engine for AI coding assistants that ingests technical docs and code repositories locally, serving grounded context via MCP to prevent hallucinations.
Overview
Qurio is a local knowledge engine that runs on your machine to ingest heterogeneous documentation (web crawls, PDFs, Markdown) and serve it directly to AI coding assistants via MCP. It features a custom structural chunker that respects code blocks, API definitions, and config files. With hybrid search combining BM25 and vector embeddings, configurable reranking, and an intuitive Vue.js admin dashboard, Qurio ensures your AI writes better code faster using only the context you trust.
Try asking AI
After installing, here are 3 things you can ask your AI assistant:
When to choose this
Choose Qurio when you need a self-hosted RAG solution for AI coding assistants that respects your privacy and processes technical documentation with structure-aware chunking.
When NOT to choose this
Don't choose Qurio if you need cloud-based deployment or require authentication/authorization for multi-user access as it's designed for localhost-only usage.
Tools this server exposes
4 tools extracted from the READMEqurio_searchSearch your knowledge base using hybrid search (keywords + vectors).
qurio_list_sourcesList all available data sources in the knowledge base.
qurio_list_pagesList pages within a specific source.
qurio_read_pageRead the complete content of a specific document or web page.
Comparable tools
Installation
Installation
Prerequisites
- [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/)
- A [Google Gemini API Key](https://aistudio.google.com/app/apikey) (for embeddings)
Steps
- Clone the repository:
``bash git clone https://github.com/irahardianto/qurio.git cd qurio ``
- Configure environment:
``bash cp .env.example .env # Add your Gemini API key to .env ``
- Start the system:
``bash docker-compose up -d ``
- Access the dashboard at http://localhost:3000
- Add additional API keys (Jina AI/Cohere) in the settings page
MCP Configuration
Add to your MCP settings:
{
"mcpServers": {
"qurio": {
"httpUrl": "http://localhost:8081/mcp"
}
}
}Compare qurio with
Last updated · Auto-generated from public README + GitHub signals.