Four ways to find answers.
One agent that knows
which to use.

RAGStack indexes your documents four ways at once — keyword, vector, knowledge-graph and SQL — then routes every question through whichever strategy suffices. Every answer is split into claims, checked against its citations, and withheld when support is thin.

The whole system, documented.

§00 · MAP

Nothing hidden behind a marketing page — every component, decision and control is written up in plain English.

Try it against your own machine.

§DEMO

This page talks to 127.0.0.1:8000 — nothing is sent to us. Start the server locally and this console goes live.

From zero to answers
in three commands.

§QS
 terminal
# install
pip install ragstack

# index a folder of documents
ragstack index ./docs

# ask — or `ragstack serve` for the console
ragstack query "how does fusion rank results?"
 python
from ragstack import RAGStack

svc = RAGStack("ragstack.yaml")
svc.ingest(["./docs"])

answer = svc.query(
    "which components depend on auth?",
    mode="agentic", session_id="team",
)
print(answer.text)
print(answer.confidence)
Full command & API reference →

Stop choosing a retrieval strategy.
Ship all of them — verified.

§END

MIT licensed. Local-first. Built to be read.

pip install ragstack View source