Docker Template Bundling Coding Agents for GPU Cloud Hosting
Melvin Vivas · X post · 2026-09-02 · Open on X
Topics: LLMOps, Deployment & Monitoring, AI Dev Tools & Productivity, Portfolio Projects · Level: intermediate
Summary
Melvin Vivas is using Codex to build a Docker image for GPU hosts like Runpod or QuickPod. The image bundles PyTorch, CUDA, several coding agents (Codex, Claude Code, Pi) and a CUDA-enabled llama.cpp. His reasoning is that coding agents are also good at AI/ML work, so a ready-made GPU environment with them already installed saves setup time.
Key points
- Coding agents can do AI/ML work, so it helps to have them installed next to the GPU.
- Template contents: PyTorch + CUDA, Codex, Claude Code, Pi and CUDA-enabled llama.cpp.
- Built to run on rented GPU hosts such as Runpod and QuickPod.
- Targets the RTX 3090 and other supported GPUs.
- He used a coding agent (Codex) to write the Docker template itself.
Resources mentioned
- Runpod · tool · x.com · paid
GPU cloud platform for running, training and serving AI models; Flash deploys workloads to it.
Also in: AI DevBox v1.3.0: a GPU-ready Docker image with coding-agent CLIs (Melvin Vivas on X · notes), Why LLM data agents need solid data foundations (Runpod) (Melvin Vivas on X · notes), Docker image with coding agents pre-installed on a CUDA + PyTorch base (Melvin Vivas on X · notes), GPU devbox Docker image with coding agents on Runpod (Melvin Vivas on X · notes) and 5 more - QuickPod · tool · console.quickpod.io · paid
A cloud service for renting GPU pods to host and run your own models.
Also in: Reusable GPU devbox: PyTorch/CUDA plus six coding agents (Melvin Vivas on X · notes), Self-Host a Coding Model on QuickPod with llama-swap and Use It in Claude Code (Melvin Vivas on X · notes) - PyTorch · tool · pytorch.org · free · recommended by both Bashiri Smith & Melvin Vivas
Deep-learning framework. Its built-in scaled dot-product attention (SDP) was the baseline in this benchmark.
Also in: Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), Wannabe vs $200K+ AI Engineer: RAG, Agents, Context and Fine-Tuning Mistakes (Bashiri Smith on Facebook · notes), AI DevBox v1.3.0: a GPU-ready Docker image with coding-agent CLIs (Melvin Vivas on X · notes), Docker image with coding agents pre-installed on a CUDA + PyTorch base (Melvin Vivas on X · notes) and 5 more - OpenAI Codex · tool · openai.com · paid · recommended by both Bashiri Smith & Melvin Vivas
OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
Also in: Developers moving from ChatGPT/Codex to Claude (Melvin Vivas on X · notes), Creator Opinion: Codex Is Still the Best at Computer Use (Melvin Vivas on X · notes), OpenAI Codex Ambassador applications are open (Melvin Vivas on X · notes), GPT-Live-1.1: Multilingual Voice Update for ChatGPT and Codex (Melvin Vivas on X · notes) and 264 more - Claude Code · tool · code.claude.com · paid · recommended by both Bashiri Smith & Melvin Vivas
Build agents and pipelines from the terminal; the guide's main agentic coding tool.
Also in: First impressions: Claude Code in the cloud is good and fast (Melvin Vivas on X · notes), Why Claude Code feels faster: gzipped turns and instant cloud sessions (Melvin Vivas on X · notes), Watch What Fills Your Coding Agent's Context and When to Clear (Melvin Vivas on X · notes), Claude Code's Right Sidebar and Context Breakdown (Melvin Vivas on X · notes) and 124 more - Pi · tool · x.com · free
A customizable coding agent that can be extended through its Extensions API and connected to several model providers.
Also in: 100-Iteration Autonomous Coding Loop with Local Qwen on an RTX 3090 (Melvin Vivas on X · notes), Pi Agent: A Highly Customizable Agent with Durable Sessions (Melvin Vivas on X · notes), Prompting an Autonomous Agent Loop: Be Specific, Show Visible Progress (Melvin Vivas on X · notes), Running an Overnight 100-Iteration Agent Loop with a Local Qwen Model (Melvin Vivas on X · notes) and 54 more - llama.cpp · repo · github.com · free
An open-source C/C++ engine for running GGUF models locally. Its llama-server command provides an OpenAI-compatible HTTP server.
Also in: Run Pi with local models on an RTX Spark laptop via llama.cpp (Melvin Vivas on X · notes), llama.app: Run Local Models on a Mac Without the llama.cpp CLI (Melvin Vivas on X · notes), Deploy Cheap Quantized GGUF Models on HF Inference Endpoints with llama.cpp (Melvin Vivas on X · notes), Run Local LLMs on the Computer You Already Have: A Beginner's Path (Melvin Vivas on X · notes) and 33 more
Try this
- Build a Docker image for a GPU cloud that comes with PyTorch, CUDA, llama.cpp and coding agents already installed.
More in LLMOps, Deployment & Monitoring
- Local Speech-to-Text with LFM2.5-Audio-1.5B and llama.cpp
- Daytona Offers GPU Sandboxes (H100, RTX 4090/5090)
- Long-Context Local LLM on an RTX 3090: .env Config and ~64 tok/s Benchmark
- Why Claude Fable 5.1 Costs Less: Cheaper Cache Reads
- Running Qwen3.8-27B EXL3 Locally on an RTX 3090 with 220K+ Context
- Serving Qwen3.8-27B (EXL3) with 262K Context on a 24GB RTX 3090