Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.remotemux.com/llms.txt

Use this file to discover all available pages before exploring further.

RemoteMux lets you run AI coding agents on a remote VM that keeps working when your laptop sleeps, your Wi-Fi drops, or your battery dies.
This guide assumes you have already run rmux env new and rmux workspace new main. If not, start with Quick Start.

​
Claude Code

Attach to your workspace and start Claude: 
cd your-project
rmux workspace attach
# Inside the remote terminal:
claude
Give Claude a task, then detach with Ctrl+B, D. The VM keeps running. Come back later: 
rmux workspace attach
# Full scrollback shows everything Claude did.

​
Claude Code Auth

RemoteMux performs a best-effort Claude Code auth sync before rmux env new, rmux workspace attach, rmux workspace new, and rmux workspace run. If Claude is authenticated locally, the remote workspace can usually use it immediately. 
rmux claude status    # check auth state locally and remotely
rmux claude login     # run Claude login flow, then sync to environment
rmux claude sync      # force sync from current local auth state

​
Codex

rmux workspace attach
# Inside the remote terminal:
codex
Detach and reconnect the same way. Any CLI agent that runs in a terminal works.

​
Codex Auth

RemoteMux also performs a best-effort Codex auth sync before rmux env new, rmux workspace attach, rmux workspace new, and rmux workspace run. When Codex is configured locally, RemoteMux syncs the first available source in this order:
  1. CODEX_API_KEY
  2. OPENAI_API_KEY
  3. ~/.codex/auth.json (including ChatGPT OAuth sessions)

​
Parallel Agents

Run multiple agents on the same project simultaneously, each in its own isolated workspace: 
rmux workspace new feature-auth
rmux workspace new feature-api
rmux workspace new refactor-db
Start a separate agent in each: 
rmux workspace attach feature-auth
# Start Claude, give it a task, detach (Ctrl+B, D)

rmux workspace attach feature-api
# Start another Claude instance, detach
Each workspace gets its own git worktree, so multiple agents can edit the same repo without merge conflicts.

​
Monitor progress

rmux workspace ls                            # list all workspaces
rmux workspace logs feature-auth --follow    # tail output without attaching
rmux env status                              # environment overview

​
Move changes back

After agents finish, use git to review, push, and merge their branches from the main workspace or from your local checkout.

​
Secrets

Agents often need API keys. Set them once per environment: 
echo 'sk-ant-...' | rmux env secrets set ANTHROPIC_API_KEY
rmux env secrets ls
Secrets are available as environment variables in all workspaces.

​
Tips

  • Use named workspaces for agents — keep main clean for manual work.
  • Detach, do not kill — Ctrl+B, D detaches without stopping anything. exit or Ctrl+D ends the session.
  • Expose ports — if an agent starts a dev server, use rmux env expose 3000 to get a public URL.
  • Stop compute when done — rmux env down stops billing while preserving workspace state.
Last modified on April 9, 2026