Claude finds the right passage in your sources

passageway indexes what your connectors report and gives Claude the best few passages for a question, with links. When nothing is relevant enough, it says nothing.

Install and run Write a connector

What it is

passageway is the retrieval half of a RAG system, served as an MCP tool. It does no generation: the model that calls it reads the passages and writes the answer.

• The core knows no source. A connector is any executable that lists items and prints their text as JSON Lines. Anyone can write one, in any language.
• It is quiet on purpose. A relevance gate lets it return nothing instead of padding a prompt with weak matches.
• It runs small. Keyword and embedding search in one SQLite file per source, on the CPU, with no vector database to run.

[[connector]]
name = "lighthouses"
command = ["/path/to/python", "-m", "passageway_connector_wikipedia"]
env = { LANGUAGE = "de", CATEGORIES = "Kategorie:Leuchtturm in Deutschland" }

flowchart LR
  A[Your connectors] -- JSON Lines --> B[passageway]
  B -- "recall tool" --> C[Claude]

Available today

• The connector protocol and a guide to writing a connector
• The Wikipedia connector, in English and German
• Hybrid search with a relevance gate, described in How it works

Coming

These are planned and not available yet: a choice of embedding models, a full evaluation harness that measures retrieval quality on your own questions and builds a report you can publish (a basic scorer, passageway.eval, exists today), a container image, a Claude Code plugin for the prompt hook, and connectors for Trilium, Confluence and folders of markdown files.