🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
CLI for a browser web terminal via ttyd and Cloudflare
Shell Now starts a temporary public web terminal from your machine. It downloads `ttyd` and `cloudflared`, then uses them to expose a shell or custom command in the browser.
Builders who want to share a live terminal in the browser for debugging, demos, or remote access.
You can open a shell in the browser in seconds instead of setting up remote access by hand.
What it does
One-command web shell
Starts a public terminal from a single CLI command.
Automatic binary setup
Downloads `ttyd` and `cloudflared` for the current platform.
Password protection
Lets you add authentication before exposing the shell.
Custom commands
Can run a shell or another command such as `htop`, `matrix`, or `bash`.
How to get it
- 1Run
# Add this tap to your Homebrew brew tap strrl/collective # Install shell-now brew install shell-now # Start shell-now shell-now
- 2Run
docker run cr.strrl.dev/strrl/shell-now:latest
README
Shell Now 🐚⚡
Instant Web Terminal via
ttyd+cloudflared— A one-click webshell for developers, educators, and hackers.
ShellNow is a tiny Go-powered CLI tool that helps you instantly start a temporary, publicly-accessible web terminal using ttyd and Cloudflare Quick Tunnels.
Ideal for quick debugging, remote terminal sharing, and Linux teaching demos.
🎥 Demo
It's a 3 min video, and it will take you 1.5 min with 2x speed, or 1.8 seconds at 100x speed.
✨ Features
- 🚀 One command to launch a public web shell
- 🧩 Automatically downloads
ttydandcloudflared(cross-platform) - 🔐 Optional password authentication
- 💻 Runs any shell or custom command (e.g.
htop,matrix,bash)
📦 Installation
Homebrew (macOS)
# Add this tap to your Homebrew
brew tap strrl/collective
# Install shell-now
brew install shell-now
# Start shell-now
shell-now
Docker
docker run cr.strrl.dev/strrl/shell-now:latest
Note: The Docker version runs in an isolated container environment separate from your host system. Use this for demos or when you want a sandboxed shell experience.
Native App Alternative
Are you an Apple fanboy and prefer a native app? See: https://github.com/amantus-ai/vibetunnel
Quick Install
# Auto-detect OS and architecture
OS=$(uname -s); ARCH=$(uname -m)
case $OS in Linux) OS="Linux";; Darwin) OS="Darwin";; esac
case $ARCH in x86_64|amd64) ARCH="x86_64";; arm64|aarch64) ARCH="arm64";; esac
curl -LO https://github.com/STRRL/shell-now/releases/latest/download/shell-now_${OS}_${ARCH}.tar.gz
tar -xzf shell-now_${OS}_${ARCH}.tar.gz
sudo install shell-now /usr/local/bin/shell-now && rm shell-now shell-now_${OS}_${ARCH}.tar.gz
📚 Why?
Sometimes you just want to…
- 🔧 Show a live bug in a terminal to a teammate
- 👨🏫 Give a quick Linux/DevOps lesson via browser
- 🧪 Share a terminal-based demo of your CLI tool
- 🏠 Remotely connect to your own Pi/NAS with no public IP setup
ShellNow makes it dead-simple.
⚠️ Warning
This tool exposes your local shell to the public internet.
- ALWAYS Use password protection
- Prefer read-only demos when possible
- Avoid running this on sensitive systems
🐛 Known Issues
- Safari Compatibility: The web terminal currently has compatibility issues with Safari browser. Use Chrome, Firefox, or Edge for the best experience.
🙌 Contributing
Pull requests, issues, and ideas are welcome!
Files in the repo
- .claude
- .github
- cmd
- hack
- pkg
- .gitignore
- .goreleaser.yaml
- CLAUDE.md
- Dockerfile
- go.mod
- go.sum
- LICENSE
- Makefile
- README.md
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More tools
The best-benchmarked open-source AI memory system. And it's free.
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
