<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ollama on probonas.net</title><link>https://yannis.probonas.net/tags/ollama/</link><description>Recent content in Ollama on probonas.net</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 27 Jun 2026 18:20:03 +0300</lastBuildDate><atom:link href="https://yannis.probonas.net/tags/ollama/index.xml" rel="self" type="application/rss+xml"/><item><title>Using Docker sbx with Claude Code and Ollama</title><link>https://yannis.probonas.net/blog/ollama-sbx-claude/</link><pubDate>Sat, 27 Jun 2026 00:00:00 +0000</pubDate><guid>https://yannis.probonas.net/blog/ollama-sbx-claude/</guid><description>&lt;p>A practical guide to running secure, local AI development environments with sandboxed isolation.&lt;/p>
&lt;hr>
&lt;p>Cloud-based LLM APIs bring cost volatility and data sovereignty risks – proprietary code leaves your control the moment it hits an external endpoint. Also running unattended agents locally introduces its own risks, while overly restrictive permissions create friction that slows development.&lt;/p>
&lt;p>The answer is to build a fully offline, local AI development environment where models run on your machine, code executes in a secure sandbox, network policies block unwanted outbound traffic, and Claude Code delivers agentic workflows without leaving your infrastructure.&lt;/p></description></item></channel></rss>