Skip to content
← Projects

02 / Support systems

Qragy · support grounded in a knowledge base

Qragy brings knowledge retrieval, conversation and human handoff into a self-hosted application.

Open source · Updated · October 2026

My contribution

Bringing retrieval, administration and human handoff together in one open-source application.

The problem

A support assistant needs more than an answer generator: relevant knowledge, a clear conversation flow and a route to a human when the answer is insufficient.

My decisions

  1. Combine full-text and vector retrieval to find relevant knowledge.

  2. Include an admin workspace, conversation state and human handoff in the same application.

  3. Use embedded storage and support multiple model providers, including local models through Ollama.

Working result

A public, self-hostable application that brings retrieval, support workflows and evaluation tools together. The repository contains installation instructions and architecture documentation.

Answer quality depends on the source documents, retrieval and chosen model. Hosting and model-provider costs vary with the setup.

Evidence & sources

Read-only public source inspection · 2026-10-02
GET https://api.github.com/repos/mahsumaktas/qragy/git/trees/main?recursive=1
Selected response fields (JSON):
{
  "repository": "mahsumaktas/qragy",
  "revision": "78312cbc7dae61eea5218b9255f35e9e2892257b",
  "public_source_paths": [
    "admin-ui",
    "package.json",
    "src",
    "tests/eval"
  ]
}
2 October 2026: read-only inspection of public files. This is source evidence, not an application run or performance test. Text record ↗

Node.js / JavaScript / LanceDB / SQLite / RAG