Running OpenClaw 2026.7.1 in Podman rootless container

This is an overview of how to run OpenClaw version 2026.7.1 in a Podman container on a home server.

Why don't I run it on my personal Windows computer using the standard method "iwr -useb https://openclaw.ai/install.ps1 | iex"?

I don't want to run an uncontrolled AI agent on a computer that has my personal data and full admin rights. That is why I prefer an isolated Podman container in rootless mode.

Why don't I use the ready-made script "./scripts/podman/setup.sh"?

• I don't want to run third-party scripts.
• I don't plan to use the OpenClaw CLI.
• I don't want unnecessary files on my server.
• I don't want to build the image (podman build) directly on the server.

I planned to run OpenClaw with a single podman run command, but it was more complicated than I thought. In this post, I want to show what the problems were and how I solved them.

Comparison of 4 LLM and agent-zero in an elementary pentest competition

My goals

1. Get new experience with autonomous AI agents → agent-zero
2. See how common (not specialized) AI agent could perform penetration tests
3. Check several actual LLMs on pentest tasks

Attention

1. This is not a real research and guide
2. agent-zero and used LLMs are not intended for pentesting
3. The results below do not indicate that the models are good or bad.
4. The penetration test target is a local copy of OWASP Juice Shop (Probably the most modern and sophisticated insecure web application)

How AI see an AI agent

The pain of image generation in Kandinsky from n8n

Input data:

• n8n Self-Hosted Community Edition 1.112.6
• Fusion Brain (Kandinsky) AI service — offers 100 free image requests per month

Goal: Create a workflow in n8n to generate images using the Fusion Brain API.

This turned out to be harder than I expected.

NVIDIA CMP 50HX for AI: A Step-by-Step Guide

I’m gradually diving into the AI world. To gain hands-on experience, I bought a GPU specifically for image generation with ComfyUI. Wanting an affordable yet efficient solution, I chose the NVIDIA CMP 50HX - a card originally designed for mining. It has 10 GB of VRAM and 446 second-generation Tensor Cores, and cost me only $75.

Since I couldn’t find a complete guide for using mining GPUs in AI, I’ll share my experience here.

What about drivers?

❌ GeForce Game Ready Driver (v560.94 in my case) didn’t work.
❌ NVIDIA’s website doesn’t offer special drivers for this card.
❌ NVIDIA A100 Data Center driver (v573.39 for Windows) also failed.
✅ The solution: Install CUDA Toolkit (v12.9.1 for me) and NVIDIA cuDNN.

After this, Windows 10 recognized the CMP 50HX without issues.