🐳 Agent Docker Runner (v0.1)

Run any Dockerized GitHub repository locally using a simple CLI.

---

🚀 Overview

Agent Docker Runner is a lightweight CLI tool that:

• Clones a GitHub repository
• Detects a Dockerfile
• Builds a Docker image
• Runs a container
• Streams logs in real time

This is the MVP (v0.1) of a larger vision:

An agentic AI system that can automatically set up and run any codebase using natural language.

---

✨ Features (v0.1)

• ✅ GitHub repo cloning
• ✅ Docker image build
• ✅ Container execution
• ✅ Real-time log streaming
• ✅ Modular architecture (agent-ready)

---

⚙️ Installation

git clone https://github.com/<your-username>/agent-docker-runner.git
cd agent-docker-runner

python -m venv venv
source venv/bin/activate   # Windows: venv\Scripts\activate

pip install -r requirements.txt

▶️ Usage

python main.py run https://github.com/ianmiell/simple-dockerfile.git

🏗️ Architecture (v0.1)

        +------------------+
        |      CLI         |
        | (Typer Interface)|
        +--------+---------+
                |
                v
        +------------------+
        |     Runner       |
        |  (core logic)    |
        +--------+---------+
                |
    ----------------------------
    |            |             |
    v            v             v
+----------+  +----------+  +----------+
| Git Tool |  | Analyzer |  | Docker   |
|          |  |          |  | Tool     |
+----------+  +----------+  +----------+
    |                          |
    v                          v
Clone Repo              Build & Run Container

📁 Project Structure

agent-docker-runner/
│
├── cli.py
├── main.py
│
├── core/
│   ├── runner.py
│   ├── analyzer.py
│
├── tools/
│   ├── git_tool.py
│   ├── docker_tool.py
│
├── utils/
│   ├── logger.py

🎯 Vision

To build a system where:

agent run "Run this repo with GPU on port 5000"

🔮 Roadmap

v0.2

Natural language input (Planner)
Port mapping support

v0.3

Dockerfile auto-generation

v0.4

Failure recovery agent

v1.0

Fully agentic DevOps system
Memory + self-improving workflows