Reusable GPU devbox: PyTorch/CUDA plus six coding agents

Melvin Vivas · X post · 2026-09-02 · Open on X

Topics: AI Dev Tools & Productivity, LLMOps, Deployment & Monitoring, Fine-tuning & Model Customization · Level: intermediate

Summary

The creator built a reusable Docker devbox (v1.1.0) for local NVIDIA GPUs or cloud GPU providers like Runpod and QuickPod. It bundles PyTorch/CUDA with the coding agents Codex, Claude Code, Pi, Grok Build and Cursor CLI, plus Herdr for persistent sessions.

Key points

• One image works on local NVIDIA GPUs, Runpod or QuickPod
• Base: PyTorch + CUDA
• Coding agents included: Codex, Claude Code, Pi, Grok Build, Cursor CLI
• Herdr keeps sessions running
• Current version is 1.1.0 on Docker Hub (melvindave/runpod-pytorch)

Resources mentioned

• melvindave/runpod-pytorch Docker image · tool · hub.docker.com · free
  Docker image for GPU ML development with coding agents, the Hugging Face CLI and nvtop pre-installed.
  Also in: GPU devbox Docker image with coding agents on Runpod (Melvin Vivas on X · notes), Ready-made Docker image for running coding agents on ML/fine-tuning jobs (Melvin Vivas on X · notes)
• 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: Docker Template Bundling Coding Agents for GPU Cloud Hosting (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
• CUDA · tool · developer.nvidia.com · free
  NVIDIA's GPU computing platform, needed for GPU-accelerated deep learning.
  Also in: AI DevBox v1.3.0: a GPU-ready Docker image with coding-agent CLIs (Melvin Vivas on X · notes), GPU-Ready AI Devbox Docker Image on Runpod (PyTorch 2.8 + CUDA 12.8) (Melvin Vivas on X · notes), Jensen Huang on NVIDIA's Long-Term Commitment to Open Nemotron Models (Melvin Vivas on X · notes)
• OpenAI Codex · tool · openai.com · paid
  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: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 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: Create Claude Code Plugins with /plugin-authoring (Melvin Vivas on X · notes), Claude Code mods: customize behavior and UI with plugins (Melvin Vivas on X · notes), AI Engineer Roadmap Overview: From ML Foundations to RAG, Agents & Ops (Bashiri Smith on Facebook · notes), SkillsBento: Free Plugin Marketplace for Codex and Claude Code (Melvin Vivas on X · notes) and 101 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: Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Pi reaches v1.0 (Melvin Vivas on X · notes), Claude Code mods: customize behavior and UI with plugins (Melvin Vivas on X · notes), Customizing Your Coding Setup with Pi Coding Agent Extensions (Melvin Vivas on X · notes) and 39 more
• Grok Build · tool · x.ai · free
  xAI's agentic coding CLI; data sharing is on by default and can be turned off with /privacy.
  Also in: Setting up Grok Bot for coding with Grok Build and Cursor CLI (Melvin Vivas on X · notes), Handing off an unfinished Codex session to Grok Build (Melvin Vivas on X · notes), Grok Build finishes a task Codex left hanging (Melvin Vivas on X · notes), Grok Build praised as a smooth, fast CLI coding tool (Melvin Vivas on X · notes) and 10 more
• Cursor · tool · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
  AI-native code editor (VS Code with AI built in).
  Also in: GLM 5.3 and GLM 5.3 Flash now in Cursor (Melvin Vivas on X · notes), Grok Bot Can Now Hand Off Coding Tasks to Cursor (Melvin Vivas on X · notes), Why Plan Mode Still Matters in AI Coding Assistants (Codex, Claude, Cursor) (Melvin Vivas on X · notes), Why Plan Mode Still Matters in AI Coding Agents (Codex, Claude, Cursor) (Melvin Vivas on X · notes) and 121 more
• herdr · tool · x.com · check price
  A runtime that keeps real terminals open for coding agents on a local or rented machine, so agent sessions keep running when you disconnect.
  Also in: Terminal Tool Recommendation: herdr (Melvin Vivas on X · notes), herdr 0.9.0: Control Agents Across Multiple Machines (Melvin Vivas on X · notes), GPU devbox Docker image with coding agents on Runpod (Melvin Vivas on X · notes), GPU-Ready AI Devbox Docker Image on Runpod (PyTorch 2.8 + CUDA 12.8) (Melvin Vivas on X · notes) and 7 more

Try this

• Pull melvindave/runpod-pytorch:1.1.0 and run it on a local NVIDIA GPU, Runpod or QuickPod
• Build your own reusable Docker devbox with your preferred ML stack and coding agents