Updating Production Code via Telegram

If you think OpenClaw is too complex for your needs and just want a straightforward way to update or fix your code using Telegram, there's a simpler alternative. An open-source project called Claude Code Telegram by Richard Atkinson allows you to send instructions over Telegram to your server running Claude Code.

This setup is minimal: no complex orchestration, no dashboards, and no exposed control planes to worry about. Just a direct path from you to Telegram, then to your server, and finally to your code.

Here's how to set it up on a DigitalOcean Droplet.

Create a DigitalOcean Droplet

First, you'll need to create a DigitalOcean Droplet. If you don't have a server yet, a basic Ubuntu droplet will do.

In the DigitalOcean control panel:

Click Create → Droplets
Choose Ubuntu (any latest LTS version will work)
Select a basic plan (the smallest size is fine for testing)
Choose your region
Add your SSH key if available
Click Create Droplet

Once your droplet is ready, connect to it via SSH with:

ssh root@your_droplet_ip

Replace your_droplet_ip with the IP address provided after creating the droplet. If you encounter an error, wait a couple of minutes and try again.

Configuring Your Droplet

After setting up your droplet, configure it to handle the necessary dependencies and services to allow message sending over Telegram to Claude Code.

Step 1. Update Package Lists

sudo apt update

Step 2. Install Zsh

sudo apt install zsh -y

Step 3. Install Essential Build Tools

sudo apt install build-essential procps curl file git -y

Step 4. Install GitHub CLI

sudo apt install gh

Authenticate the GitHub CLI by running:

gh auth login

Follow the prompts, selecting GitHub.com, choosing HTTPS, and using a generated token with repo and read:org permissions.

Step 5. Install Oh My Zsh

sh -c "$(curl -fsSL https://raw.githubusercontent.com/ohmyzsh/ohmyzsh/master/tools/install.sh)"

Step 6. Install Python Dependencies

sudo apt install -y curl python3-venv python3-pip

Step 7. Generate an SSH Deploy Key

ssh-keygen -t ed25519 -C "do-droplet-deploy-key" -f ~/.ssh/github_deploy_key

Step 8. Add the Public Key to GitHub

Fetch your public key with:

cat ~/.ssh/github_deploy_key.pub

Copy and add it to GitHub under SSH and GPG keys.

Step 9. Configure SSH to Use the Key

cat >> ~/.ssh/config <<'EOF'
Host github.com
  HostName github.com
  User git
  IdentityFile ~/.ssh/github_deploy_key
  IdentitiesOnly yes
EOF

Step 10. Lock Down SSH Config Permissions

chmod 600 ~/.ssh/config

Step 11. Pre-Register GitHub’s Host Identity

ssh-keyscan -H github.com >> ~/.ssh/known_hosts

Step 12. Set known_hosts Permissions

chmod 644 ~/.ssh/known_hosts

Step 13. Install Poetry

curl -sSL https://install.python-poetry.org | python3 -

Step 14. Add Poetry to Your PATH

echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc
source ~/.zshrc

Step 15. Verify Poetry Installation

poetry --version

Install Claude Code

Step 1. Install Claude Code

curl -fsSL https://claude.ai/install.sh | bash

Step 2. Set Your Anthropic API Key

nano ~/.zshrc

Add the following line with your API key:

export ANTHROPIC_API_KEY="sk-..."

Reload:

source ~/.zshrc

Step 3. Clone Claude Code Telegram

git clone git@github.com:RichardAtCT/claude-code-telegram.git
cd claude-code-telegram

Step 4. Install Bot Dependencies

make dev

Ignore any warnings about pre-commit not being configured.

Set Up Telegram

Step 1. Create a Telegram Bot

In Telegram:

Message @BotFather
Run /newbot
Choose a name ending with bot
Save the token

Step 2. Configure the Bot

mkdir /root/projects
cp .env.example .env
nano .env

Populate the .env file with:

TELEGRAM_BOT_TOKEN=<your token>
TELEGRAM_BOT_USERNAME=<your bot username>
APPROVED_DIRECTORY=/root/projects
ALLOWED_USERS=<your Telegram user ID>
USE_SDK=true

Step 3. Run the Bot

For the first run, use debug mode:

make run-debug

For normal operation, use:

make run

Conclusion

With this setup, you can send commands via Telegram like: "Let’s remove the about link from the header nav on the repository." Claude Code will then process the request locally on your server, make the necessary changes, and send a response back over Telegram. This approach offers a simple and effective way to manage code without the complexity of more extensive frameworks.