unb-consultant

Universal NotebookLM-Based Consultant. Create and query AI experts powered by Google Gemini Notebook (formerly NotebookLM).

Installation

pipx install "unb-consultant[browser]"

Or with cookie extraction support:

pipx install "unb-consultant[browser,cookies]"

Quick Start

# Authenticate
unb login

# Create an expert
unb expert create "cvss-v4" \
  --url "https://www.first.org/cvss/v4-0/specification-document" \
  --desc "CVSS v4.0 scoring expert"

# Ask a question
unb ask "cvss-v4" "How is the base score calculated?"

# List experts
unb expert list

MCP Server

For AI agent integration, start the MCP server:

unb mcp

Then configure in your opencode.json:

{
  "mcpServers": {
    "unb-consultant": {
      "command": "unb",
      "args": ["mcp"]
    }
  }
}

Commands

Command	Description
`unb login`	Authenticate with Google
`unb auth check --test`	Verify authentication
`unb expert create NAME`	Create a new expert
`unb expert list`	List all experts
`unb expert delete NAME`	Delete an expert
`unb ask NAME QUESTION`	Ask a question
`unb catalog NAME`	Generate thematic catalog
`unb skill-gen NAME`	Generate SKILL.md
`unb source add NAME`	Add sources to expert
`unb mcp`	Start MCP server
`unb setup`	Interactive setup

Metadata

Release files for unb-consultant 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for unb-consultant 0.1.0
File	Size	Uploaded
unb_consultant-0.1.0.tar.gz	26.6 kB	Jul 20, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for unb-consultant 0.1.0
File	Interpreter	ABI	Platform	Reset
unb_consultant-0.1.0-py3-none-any.whl 30.5 kB Jul 20, 2026	Python 3	none	any	Details

Total release size: 57.1 kB

Release files / unb_consultant-0.1.0.tar.gz

Download URL	unb_consultant-0.1.0.tar.gz
Size	26.6 kB
Tags	Source
SHA-256 checksum How to use checksums	`705139a959a84af410529c05573f2dbcdecaa3820f8fde72ce9fc907471c963d`
BLAKE2b-256 checksum How to use checksums	`585f001e570775dec40c5238fbb69b6a53c571c4f8e4049788886afe3ba77077`
Upload date	Jul 20, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.11.5`

Release files / unb_consultant-0.1.0-py3-none-any.whl

Download URL	unb_consultant-0.1.0-py3-none-any.whl
Size	30.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`5032c374c5558ad9cd3b5ef3710ef4b519baeaaa58223ae9aa21d08180a84361`
BLAKE2b-256 checksum How to use checksums	`c5c371551177b4369d2649e317af45f2be821a0d957724e943dafaf15bb8fec1`
Upload date	Jul 20, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.11.5`