Community project · for Luxor sandboxes

An agent in a box, one command away.

Run Claude Code, Codex or any of 26 coding agents in a Luxor sandbox. One command makes the box, starts the agent and drops you in. Close the laptop and it keeps working. Pick it up again from your phone. Let it run with approvals off, in a box that is nobody's machine.

Claude CodeCodexopencodeCopilotGemini CLIQwen CodeCrushGooseKimi CodeOoh-my-piAdaLHermesOpenClawPiDroidGrok BuildAmpPrime AgentTinyFishAnchorHotdataOpen WebUI
install.sh · macOS & Linux
$curl -fsSL https://luxcode.org/install.sh | sh

Installs lux into ~/.local/bin. Needs the Luxor CLI and jq. llms.txt for agents.

26 coding agents, each in its own sandbox: 21 in the terminal, 5 as web UIs

What you get

The box, and the agent in it.

Luxor gives you the sandbox. luxcode turns it into a coding agent you can reach from anywhere.

The box

The box is just there

You never create or resume a sandbox by hand. Run any lux command and the box is simply there: made if it does not exist yet, woken if it was paused, waited for if it is still starting. New boxes start from a golden image with tmux already in it. A persistent volume at ~/work outlives the box, and rm keeps it: name the agent again and it comes back on its files.

Auto-resumePersistent volumesGolden image2 to 16 vCPULuxor's own images
The agent

Your agent, your models

Pick a terminal agent or a web UI, then where it thinks: the agent's own sign-in, or Nebius, Boundless, Baseten, Friendli and OpenRouter. No config file to edit, and the key never touches your shell history. The agent runs in tmux, so it survives disconnects and pauses; lux <agent> drops you back into the same conversation.

Remote Control for Claude CodetmuxHeadless runsPrivate tunnelsKeys stay on your machine
Agents

Every coding agent. Each one gets its own box.

lux new asks terminal or web first, then which agent. Each gets a sandbox named after it, independent of the others.

Terminal · in tmux

Installed on first use

Claude Code, Codex and opencode come with the base image; the rest install into the box the first time, once.

claudecodexopencodecopilotgeminiqwencrushgoosekimiompadalhermesopenclaw
Luxor images

Luxor's own images

Pi, Droid, Grok Build, Amp, Prime Agent, TinyFish, Anchor and Hotdata ship as Luxor sandbox images. The box starts from the image, pinned and ready, with your key or a sign-in inside.

pidroidgrokampprime-agenttinyfishanchorhotdata
Web UIs

Private by default

lux opens an ssh tunnel and your browser on it. lux <agent> url makes a public Luxor link, and anyone with it gets in. Terminal agents get the same: a browser terminal on the agent's session, behind a password.

opencode-web :8086open-webui :8083hermes-web :8088openclaw-web :8087durable-pi :8092
Inference providers

The agent's own sign-in, or bring your own models

The providers in the second half of the table work with every agent that takes a custom endpoint. Keys are asked for once and kept on your machine, mode 0600.

ProviderKeyDefault modelNote
Each agent's default — its own sign-in or key, set once inside the box
Anthropicsign in inside the boxClaude's ownClaude Code — the only provider with Remote Control (claude.ai/code, from your phone)
OpenAIcodex login insideCodex's ownCodex
opencodeconfigured inside opencodeopencode's ownopencode and opencode-web; any provider in opencode's catalog
GitHub/login insideCopilot's ownCopilot — needs a Copilot plan
GoogleGoogle sign-in insideGemini's ownGemini CLI
QwenQwen OAuth insideQwen's ownQwen Code
Moonshotkimi login insideKimi's ownKimi Code
FactoryFACTORY_API_KEY, or droid login insideDroid's ownDroid
xAIXAI_API_KEY, or grok login insideGrok's ownGrok Build
AmpAMP_API_KEY, or amp login insideAmp's ownAmp
Prime IntellectPRIME_API_KEY, or sign in insidePrime's ownPrime Agent
TinyFishTINYFISH_API_KEY—TinyFish, a web-agent toolkit
Anchor BrowserANCHOR_API_KEY—Anchor, a browser-automation toolkit
HotdataHOTDATA_API_KEY (and HOTDATA_WORKSPACE if your account needs it)—Hotdata, a data toolkit
The app's own setupconfigured inside the appits ownCrush, Goose, Pi, oh-my-pi, adal, Hermes, OpenClaw, Open WebUI
Bring your own models — one key, works with every agent that takes a custom endpoint
Nebius Token FactoryNEBIUS_API_KEYmoonshotai/Kimi-K3no Anthropic API: Claude Code goes through a translation proxy in the box
BoundlessBOUNDLESS_API_KEYclaude-fable-5.1Anthropic and OpenAI APIs
BasetenBASETEN_API_KEYmoonshotai/Kimi-K3Anthropic API in beta
FriendliFRIENDLI_TOKENzai-org/GLM-5.3
OpenRouterOPENROUTER_API_KEYanthropic/claude-fable-5.1every model behind one key
Usage

Three commands from zero to a running agent.

$from zero
curl -fsSL https://luxcode.org/install.sh | sh    lux into ~/.local/bin
lux login                                         your Luxor account, once
lux                                               pick an agent, or make one, and you are in
$lux help
lux                        pick an agent (or create one) and jump into it
lux new [cli|web|harness]  create: terminal or web → agent → provider → model → size → volume → name
lux <agent> [action]       a specific agent by name (or a harness name: your agent for it)

up        (default)  create or resume the box, start the agent, attach
shell                plain shell in the box
run -- <prompt>      one-shot headless prompt
status               agent, provider, box state
provider | model     switch inference provider, or model
size | volume        box size (next create) · persistent volume at ~/work
url [off]            a public link: the web UI, or a browser terminal — anyone with it gets in
auth                 sign in, or store or replace the provider key
down | pause         pause the box (woken by the next command)
rm [--purge]         terminate the box; the volume is kept unless --purge

lux ls                     agents, their boxes, and kept volumes
lux volumes [rm <name>]    every volume; delete one for good
lux config [<name> <value>] settings and keys; save a default
lux auth [provider]        store or replace a provider key
lux image [build]          the golden image new boxes start from
lux pause --all · lux rm --all [--purge]
Sizes
  • small2 vCPU · 4 GiB
  • medium4 vCPU · 8 GiB default
  • large8 vCPU · 16 GiB
  • xlarge12 vCPU · 32 GiB
  • xxlarge16 vCPU · 64 GiB

A box is not resized in place: size applies on the next create.

Volumes
  • where~/work, the agent starts there
  • sizes10, 25 or 50 GiB
  • survivespause, rm, resizing
  • keptrm keeps it; lux <name> brings the agent back on it
  • fixeda volume keeps its size for life

Pick generously. lux volumes lists them; lux volumes rm deletes one for good.

Headless
lux nebius-codex run -- "fix the failing test"

Runs one prompt and exits, with the provider wired in.

lux tinyfish run -- fetch content get https://…

Toolkits take raw arguments for their own CLI.

Pausing

Boxes pause by themselves and wake on your next command

Luxor pauses a box two hours after it starts or wakes, even mid-task: that is Luxor's limit, not a setting. Every lux command wakes a paused box, and the clock starts again. tmux and the agent's conversation survive a pause; /tmp and open connections do not. For a job that must run unattended for longer, LUX_STICKY=1 makes a box that never pauses itself, and so never stops costing until you pause it.

Configuration

Saved with lux config <name> <value>, or set in the environment for one run.

LUX_HARNESSclaudeagent used when you omit one
LUX_SIZEmediumdefault box size offered
LUX_VOLUME_GB10default volume size offered (0 = none)
LUX_DISK_GB20root disk
LUX_IMAGE—force one registry image for every agent without its own
LUX_MAX_DURATION2hpause this long after each create or resume (Luxor's cap)
LUX_PAUSE_RETENTION720hhow long a paused box is kept
LUX_STICKY01 creates boxes that never pause by themselves
Get started

Your Luxor account, your keys, your sandbox.

luxcode is free and open source: one bash script around the Luxor CLI.