A coding agent in a Luxor box colincode.org
01Claude Code2026

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://colincode.org/install.sh | sh

installs colin into ~/.local/bin · needs the Luxor CLI and jq · llms.txt

02Why it existsglue

Luxor gives you the sandbox. This makes it an agent.

The box is just there

You never create or resume a sandbox by hand. Run any colin 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, found or built on first use.

Survives everything

The agent runs in tmux inside the box. Close the laptop, lose the Wi-Fi, let the box pause: colin <agent> drops you back into the same conversation. A volume at ~/work outlives the box itself, and rm keeps it: name the agent again and it comes back on its files.

Your models

Point any agent at Nebius, Boundless, Baseten, Friendli or OpenRouter from an arrow-key menu, or keep its own sign-in. No config file to edit. Keys are asked for once, kept on your machine with mode 0600, and never touch your shell history.

03Agents21 + 5

Every coding agent. Each one gets its own box.

colin new asks terminal or web first, then which agent. Each gets a sandbox named after it, independent of the others: colin claude down never touches your crush box.

Terminal · in tmux
  • claudeRemote Control from claude.ai/code
  • codexOpenAI
  • opencode
  • copilotGitHub
  • geminiGoogle
  • qwenAlibaba
  • crushCharm
  • gooseBlock
  • kimiMoonshot
  • ompoh-my-pi
  • adalSylphAI
  • hermesNous Research
  • openclaw
Luxor images · the box starts from the image
  • piany provider, or /login
  • droidFactory
  • grokxAI Grok Build
  • ampSourcegraph
  • prime-agentPrime Intellect
  • tinyfishweb agent toolkit
  • anchorAnchor Browser
  • hotdatadatabases per task
Web UIs · private by default, url for a public link
  • opencode-web:8086
  • open-webui:8083
  • hermes-web:8088
  • openclaw-web:8087
  • durable-pi:8092

Served from the box, reached over an ssh tunnel your browser opens on. Nothing is public until colin <agent> url makes a Luxor preview link.

04Inference providersbring your own

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

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

The model menu shows about ten recommended models, then everything the provider's /v1/models returns; type to filter. A third-party provider is written into the agent's own config inside the box, and Claude Code loses Remote Control on any base URL that is not Anthropic's.

05Usagecolin help

Three commands from zero to a running agent.

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

colin ls                     agents, their boxes, and kept volumes
colin volumes [rm <name>]    every volume; delete one for good
colin config [<name> <value>] settings and keys; save a default
colin auth [provider]        store or replace a provider key
colin image [build]          the golden image new boxes start from
colin pause --all · colin 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

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; colin <name> brings the agent back on it
  • fixeda volume keeps its size for life

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

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

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

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

Toolkits take raw arguments for their own CLI.

06Pausing & configuration2h

Boxes pause by themselves and wake on your next command.

Pausing

Luxor pauses a box two hours after it starts or wakes, even mid-task: that is Luxor's limit, not a setting. Every colin 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, so an agent paused mid-request retries when the box is back. For a job that must run unattended for longer, COLINCODE_STICKY=1 makes a box that never pauses itself, and so never stops costing until you pause it.

Environment

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

COLINCODE_HARNESSclaudeagent used when you omit one
COLINCODE_SIZEmediumdefault box size offered
COLINCODE_VOLUME_GB10default volume size offered (0 = none)
COLINCODE_DISK_GB20root disk
COLINCODE_IMAGE—a registry image for every agent without its own
COLINCODE_MAX_DURATION2hpause this long after each create or resume (Luxor's cap)
COLINCODE_PAUSE_RETENTION720hhow long a paused box is kept
COLINCODE_STICKY01 creates boxes that never pause by themselves
Start

Have a box that needs an agent?

GitHubllms.txtLuxor.ai
‹ luxcode / colincode