<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Coding Agents on InternetException</title><link>https://internetexception.com/tags/coding-agents/</link><description>Recent content in Coding Agents on InternetException</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 14 May 2026 15:56:03 +0200</lastBuildDate><atom:link href="https://internetexception.com/tags/coding-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Junie Coding Agent short review</title><link>https://internetexception.com/2026/05/13/junie-coding-agent-short-review/</link><pubDate>Wed, 13 May 2026 07:40:03 +0200</pubDate><guid>https://internetexception.com/2026/05/13/junie-coding-agent-short-review/</guid><description>&lt;p&gt;I have been running few coding agents in my spare time on my personal projects and Junie does not look great when paired with local model&lt;/p&gt;&#10;&lt;p&gt;First of all, local models are capable but their ability to answer prompts in sustainable speeds degrades very quickly. I was experimenting with Qwen3.6-35B-A3B and Qwen3.5-35B-A3B. Both seems to be fairly capable, which is great for a local model that can run on decent GPU that is few years old (I have Radeon 7900 XTX with 24GB of VRAM) - that is outstanding considering what we thought about computers i.e. ten years ago. If someone then would say to me that we will be able to converse with our applications in human language and instruct them to do useful stuff, I would say: &amp;lsquo;Impossible!&amp;rsquo;. But we can and it does work but it have limitation, mainly in context size.&lt;/p&gt;</description></item><item><title>Using Mistral Vibe with local model</title><link>https://internetexception.com/2026/04/24/using-mistral-vibe-with-local-model/</link><pubDate>Fri, 24 Apr 2026 22:00:00 +0200</pubDate><guid>https://internetexception.com/2026/04/24/using-mistral-vibe-with-local-model/</guid><description>&lt;p&gt;Vibe was the first coding agent I tried to use with local model. It works and it is fun to have ability to to just tell the computer to do something you want in plain English or even in your own language if your model support it.&lt;/p&gt;&#10;&lt;h2 id="installation-and-configuration"&gt;Installation and Configuration&lt;/h2&gt;&#10;&lt;p&gt;There are several installation methods for vibe that are available along to the usual, security nightmare of running of piping curl-downloaded scripts directly to bash :)&lt;br&gt;&#10;I advise using other installation methods for example via &lt;code&gt;uv&lt;/code&gt;:&lt;/p&gt;</description></item><item><title>Using Junie agent CLI with local model</title><link>https://internetexception.com/2026/04/24/using-junie-agent-cli-with-local-model/</link><pubDate>Fri, 24 Apr 2026 19:04:03 +0200</pubDate><guid>https://internetexception.com/2026/04/24/using-junie-agent-cli-with-local-model/</guid><description>&lt;p&gt;Jet Brains have their own coding agent. Since I am already using Rider and all coding agents are pretty slow and inefficient with what they do I wanted to test if Junie have better integrations with IDE which would make things much faster.&lt;/p&gt;&#10;&lt;p&gt;For example if you will have following unused namespace in Rider.&lt;/p&gt;&#10;&lt;img src="https://internetexception.com/wp-content/uploads/2026/04/image-1.png" class="wp-image-1250" /&gt;&#10;&lt;p&gt;Removing it all cleaning all unused namespaces in entire project or even entire solution is just few clicks away. Or key strokes.&lt;/p&gt;</description></item><item><title>AI agent critique of itself</title><link>https://internetexception.com/2026/04/23/ai-agent-critique-of-itself/</link><pubDate>Thu, 23 Apr 2026 11:30:40 +0200</pubDate><guid>https://internetexception.com/2026/04/23/ai-agent-critique-of-itself/</guid><description>&lt;p&gt;I like to self-host my own services. I have my own email server. I have my own cloud storage and sync and backup. I want to have this secure and safe while having my data private.&lt;/p&gt;&#10;&lt;p&gt;But I need to learn and be up to date with current technology.&lt;/p&gt;&#10;&lt;p&gt;I decided to use &lt;a href="https://junie.jetbrains.com/docs/junie-cli.html" target="_blank" rel="noopener noreferrer"&gt;Junie&lt;/a&gt;&#10; with my own, &lt;a href="https://internetexception.com/2026/03/26/swapping-vllm-to-llama-cpp/"&gt;self hosted models&lt;/a&gt;&#10; that I run on my own &lt;a href="https://internetexception.com/2026/03/04/desktop-framework-ai-assistant-part-1/"&gt;hardware&lt;/a&gt;&#10;. In the docs they say it can be run on top your own custom provider and model. But it does not work with Rider plugin. You are limited to their own limited list of models.&lt;/p&gt;</description></item></channel></rss>