Plugin

lux-dev

By punt-labs

Visual output surface for Claude Code: display text, images, tables, plots, and interactive elements

What's Inside

Slash Commands1

/lux command

/lux

Enable or disable lux

Skills3

beads

/beads

Display a beads issue board in the Lux window with filterable table and detail panel. Use when the user asks to "show beads", "show the board", "show issues", "beads board", "beads UI", "display backlog", "show my work", or wants to visually browse project issues. Also triggered by "issue board", "task board", "kanban", "backlog view", or "bd ready in lux".

dashboard

/dashboard

Display a dashboard in the Lux window with metrics cards, charts, and status tables. Use when the user asks to "show a dashboard", "display metrics", "visualize status", "show KPIs", "monitor progress", or wants a visual overview of data. Also triggered by "build a dashboard", "metric cards", or "status overview".

data-explorer

/data-explorer

Display an interactive data explorer in the Lux window with filterable tables, search inputs, and detail panels. Use when the user asks to "explore data", "browse results", "filter a table", "search through records", "show me the data", or wants to interactively navigate tabular data. Also triggered by "data viewer", "record browser", "filterable table", or "drill into the data".

Hooks1

Event Hooks

Bash

3 hooks across 2 events

MCP Servers1

lux

Stats

Version0.21.0

ReleasedJul 23, 2026

LanguagePython

Stars0

MaintenanceExcellent

LicenseMIT

Last CommitJul 25, 2026

AddedMar 18, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Available In

punt-labs

Safety Signals

Caution

Executes bash commands

Hook triggers when Bash tool is used

lux

A visual output surface for AI agents.

Lux gives agents and apps a shared visual surface. The intended architecture is a hub/display split: clients send UI descriptions to luxd, the Hub owns authoritative element state and behavior, and the Display renders a replica of the current scene while forwarding user interactions back to the Hub.

The design draws on X11's client/server split and Smalltalk-style live introspection. MCP is one gateway into Lux, not the whole architecture. If you want the short version of the rewrite target, start with docs/architecture/target/target.md. If you need help navigating the docs, use docs/README.md. For the product direction, positioning, and risk assessment — the Working Backwards PR/FAQ — see prfaq.pdf.

Platforms: macOS, Linux

Stage: alpha --- protocol is stable, published on PyPI as punt-lux

A Claude Code plugin displaying a project issue board --- the agent fetches live data from DoltDB via bd list --json, builds a filterable table with detail panel, and renders it in a single tool call. Filters and row selection run at 60fps with zero MCP round-trips.

Beads issue board with filterable table and detail panel

The same list/detail pattern generalizes to any tabular data. Search, combo filters, pagination, and a detail panel --- all driven by a single show_table() call.

Filterable data explorer with detail panel

Dashboards compose metric cards, charts, and tables. show_dashboard() builds the layout from structured data --- no manual element positioning needed.

Dashboard with metrics, charts, and data table

Quick Start

curl -fsSL https://raw.githubusercontent.com/punt-labs/lux/00c88f6/install.sh | sh

Restart Claude Code twice. The Lux display window opens automatically when agents send visual output.

Manual install (if you already have uv)

uv tool install 'punt-lux[display]'

Then install the plugin via the marketplace:

claude plugin marketplace add punt-labs/claude-plugins
claude plugin install lux@punt-labs

Lightweight install (CLI and protocol types, no renderer)

If you only need the lux CLI and the JSON protocol element types --- enough to drive a running luxd over its REST API and to build element trees in Python --- install the base package:

uv add punt-lux

This pulls ~2 MB of lightweight deps. The 66 MB display stack (imgui-bundle, numpy, Pillow, PyOpenGL) is only needed to run the renderer (lux display) and is available via punt-lux[display].

Verify before running

curl -fsSL https://raw.githubusercontent.com/punt-labs/lux/00c88f6/install.sh -o install.sh
shasum -a 256 install.sh
cat install.sh
sh install.sh

Run a demo

lux display &
uv run python demos/dashboard.py

Demos are in demos/ --- each connects as a client and drives the display:

Demo	What it shows
`interactive.py`	Sliders, checkboxes, combos, text inputs, color pickers
`containers.py`	Windows, tab bars, collapsing headers, groups
`dashboard.py`	Multi-window layout with draw canvases and live controls
`data_viz.py`	Tables, plots, progress bars, spinners, markdown
`menu_bar.py`	Custom menus, event handling, periodic refresh

lux-dev

What's Inside

lux-dev

Popularity

What's Inside

Confidence

README

lux

Quick Start

Features

Similar Plugins

vizro-e2e-flow

Tableau Dashboard Plugin

fluxwing-skills

mui-expert

lens

Prism

More by punt-labs

prfaq-dev

beadle-dev

z-spec

quarry-dev

ethos-dev

lux

Quick Start

Features

Popularity

Health & Quality

More by punt-labs

prfaq-dev

beadle-dev

z-spec

quarry-dev

ethos-dev

Similar Plugins

vizro-e2e-flow

Tableau Dashboard Plugin

fluxwing-skills

mui-expert

lens

Prism