DEV Community

Tamiz Uddin
Tamiz Uddin

Posted on Originally published at tamiz.pro

Building a $5.70/Month Autonomous AI Coding Agent in the Cloud Using Open-Source Terminal Agent Management

#ai #machine #learning #70

Originally published on tamiz.pro.

Introduction

Autonomous AI coding agents promise to reduce developer friction by running continuously in the cloud, writing, testing, and refactoring code without human intervention. Commercial offerings like GitHub Copilot Workspace or Replit Agent cost $10–$20/month per seat. This guide shows how to build an equivalent autonomous coding agent for just $5.70/month, using open-source tools agent-deck and orca, running on a minimal cloud VM.

We'll cover:

  • Deploying a lightweight Ubuntu VM on a budget cloud provider
  • Installing agent-deck to manage terminal-based AI agents
  • Configuring orca, a minimal CLI agent runtime
  • Wiring up autonomous git pushes, test runs, and issue triage
  • Securing access with SSH keys and restricting shell permissions

Prerequisites

Before starting, ensure you have:

  • A DigitalOcean or Vultr account (or equivalent)
  • Basic familiarity with Linux, SSH, and Git
  • An OpenAI-compatible API key (OpenAI, Anthropic via proxy, or local LLM endpoint)
  • A GitHub or GitLab repository to operate on

Step 1: Provision the Cloud VM

Create a minimal Ubuntu 22.04 droplet (1 CPU, 1 GB RAM, 25 GB SSD):

# Example using DigitalOcean CLI (doctl)
doctl compute droplet create ai-agent \
  --image ubuntu-22-04-x64 \
  --size s-1vcpu-1gb \
  --region nyc3 \
  --ssh-keys <your-ssh-key-id> \
  --wait
Enter fullscreen mode Exit fullscreen mode

Cost: ~$5/month. Smaller plans exist but may be too constrained for agent workloads.

SSH into the machine:

ssh root@your-vm-ip
Enter fullscreen mode Exit fullscreen mode

Step 2: Install Dependencies

Update packages and install essentials:

apt-get update && apt-get upgrade -y
apt-get install -y git curl python3 python3-pip docker.io
pip3 install --upgrade pip
Enter fullscreen mode Exit fullscreen mode

Step 3: Install agent-deck

agent-deck is an open-source terminal session manager designed for orchestrating AI agents. It exposes a tmux-like interface and can spawn multiple agent sessions.

curl -fsSL https://raw.githubusercontent.com/humanlayer/agent-deck/main/install.sh | bash
source ~/.bashrc
Enter fullscreen mode Exit fullscreen mode

Verify installation:

agent-deck --version
Enter fullscreen mode Exit fullscreen mode

Step 4: Install orca

orca is a minimal CLI runtime for running terminal-based AI agents. It supports plugin-style workflows and integrates with agent-deck.

git clone https://github.com/humanlayer/orca.git
cd orca
pip3 install .
Enter fullscreen mode Exit fullscreen mode

Configure orca with your LLM provider:

orca config set llm.provider openai
orca config set llm.api_key $OPENAI_API_KEY
Enter fullscreen mode Exit fullscreen mode

Export the API key securely:

echo 'export OPENAI_API_KEY="your-api-key-here"' >> ~/.bashrc
source ~/.bashrc
Enter fullscreen mode Exit fullscreen mode

Step 5: Bootstrap the Agent Environment

Clone the target repository:

git clone git@github.com:your-org/your-repo.git
cd your-repo
Enter fullscreen mode Exit fullscreen mode

Start an agent-deck session:

agent-deck new my-agent
Enter fullscreen mode Exit fullscreen mode

Inside the session, launch orca:

orca agent --name coder --prompt "You are a senior engineer maintaining this repo. Fix bugs, write tests, and commit improvements autonomously." --workdir /path/to/repo
Enter fullscreen mode Exit fullscreen mode

Step 6: Enable Autonomous Git Operations

Allow the agent to commit and push changes:

orca plugin add git-commit
orca plugin add git-push
Enter fullscreen mode Exit fullscreen mode

Ensure SSH credentials are available:

ssh-agent bash
ssh-add ~/.ssh/id_ed25619
Enter fullscreen mode Exit fullscreen mode

Security note: Use a deploy key with limited push permissions instead of your personal SSH key.

Step 7: Automate Test Execution

Add a test runner plugin:

orca plugin add test-runner --cmd "make test"
Enter fullscreen mode Exit fullscreen mode

Configure orca to run tests after each commit:

orca hooks add post-commit "orca run test-runner"
Enter fullscreen mode Exit fullscreen mode

Step 8: Schedule the Agent

Use cron to restart the agent daily:\n

crontab -e
Enter fullscreen mode Exit fullscreen mode

Add:

```cron\0 9 * * * agent-deck send "my-agent" "orca agent --name coder --prompt '...' --workdir /path/to/repo' > /dev/null 2>&1




---

## Step 9: Monitor Agent Sessions

List active sessions:



```bash
agent-deck ls
Enter fullscreen mode Exit fullscreen mode

Attach to a session:

agent-deck attach my-agent
Enter fullscreen mode Exit fullscreen mode

Cost Breakdown

Resource Monthly Cost
VM (1vCPU, 1GB) $5.00
Storage $0.50
Outbound Bandwidth $0.20
Total $5.70

Savings vs. Copilot Workspace ($20/month): 71% cheaper.

Security Considerations

  • Restrict shell access via SSH keys only
  • Use a dedicated GitHub deploy key with write-only access
  • Run the agent under a non-root user
  • Regularly audit agent-deck sessions and orca logs

Frequently Asked Questions

Q: Can I use a local LLM instead of OpenAI?

A: Yes. Point orca to any OpenAI-compatible endpoint (e.g., Ollama, vLLM).

Q: How do I prevent the agent from deleting files?

A: Add a pre-execution hook that blocks destructive commands like rm -rf.

Q: What happens if the agent produces bad code?

A: All changes go through git commits. Use branch protection rules and require PR reviews before merging.

Top comments (0)