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 · 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 - 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: Finding Cursor Cloud Agents After the Cursor–X Unification (Melvin Vivas on X · notes), Overnight notebook generation with Grok Bot, Cursor cloud and Grok 4.7 (Melvin Vivas on X · notes), Gemini 4 Argon in Cursor: CursorBench Score and Pricing (Melvin Vivas on X · notes), SpaceX AI / Cursor Ambassador Program Waitlist (Melvin Vivas on X · notes) and 135 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
More in AI Dev Tools & Productivity
- Gemini 3.8 Flash Available in Cursor CLI
- Pi's /thinking Command: Choose the Model's Reasoning Level
- Setting up Grok Bot for coding with Grok Build and Cursor CLI
- Using Codex (GPT 5.6 Luna) to Build Docker Templates for Runpod
- Update Pi to Get the Thinking Level Selector
- Codex Workflow: Try GPT-5.6 Luna First, Escalate to Sol