FoF David Deutsch projects — CLI & MCP

CLI & download

Download the QRAG ? QRAG stands for Question Retrieval Augmented Generation. Focus on Foundations indexes questions and answers extracted from interviews, meetings, and books in a vector database. Semantic search finds relevant Q&A by meaning, rather than only by matching keywords, and returns quoted source passages with source links. The qrag-search skill retrieves those passages without generating an AI answer. The qrag-ask skill and web chat also give the retrieved passages to an AI model to synthesize an answer, with the direct quotes available for checking. Browse Transcripts to read the source material. An AI answer is a synthesis, not a verbatim statement by the original speaker. QRAG is open source. Point an AI agent to the public repository to ask questions about how it works, with explanations tailored to your background and interests.
https://github.com/randalljam/fof-mono-public Copy explanation Close toolkit 0.1.0 with the command-line tool, Python library, MCP server, and bundled AI Agent Skills. Python 3.10 or later is required.

Download CLI MCP Toolkit ZIP

With pipx installed, open a terminal in the folder where you saved the ZIP and run:

pipx install "./fof-qrag-0.1.0-8314f338e1a4.zip"

Then review the privacy notice and search the Deutsch corpus:

fof-qrag init
fof-qrag search "Why are good explanations hard to vary?"

Use fof-qrag ask for an AI answer, or fof-qrag --help for all commands. Public search and excerpts work without an account; full transcripts and restricted models require appropriate access.

Command examples

Deutsch is the default corpus. Search finds source passages; ask creates an AI answer. Account access and usage limits apply to AI calls and full transcripts.

Find passages and ask follow-up questions

fof-qrag search "What makes an explanation good?"
fof-qrag ask "What is the role of criticism in creating knowledge?"
fof-qrag ask "How does that connect to progress?" -c last

Browse transcripts and saved conversations

fof-qrag transcripts list popper
fof-qrag conversations list
fof-qrag conversations show last

Check your setup and available commands

fof-qrag status
fof-qrag access status
fof-qrag --help

MCP setup

The MCP server is included in the toolkit download. After installing the CLI with pipx, add its MCP dependency:

pipx inject fof-qrag "mcp>=1.10,<2"

Run fof-qrag init in a terminal to review the privacy notice before connecting your AI Agent. For Claude Code:

claude mcp add fof-qrag -- fof-qrag-mcp

For another MCP client, configure fof-qrag-mcp as its server command with stdio transport. The server provides search, AI Q&A, transcript, and conversation tools, using Deutsch by default.