<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: Nayjest</title><link>https://news.ycombinator.com/user?id=Nayjest</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 12 Oct 2026 11:13:14 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=Nayjest" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: Gito v4.1.0 – AI code reviewer now runs on Claude Code / Gemini CLI]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/Nayjest/Gito/releases/tag/v4.1.0">https://github.com/Nayjest/Gito/releases/tag/v4.1.0</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48415164">https://news.ycombinator.com/item?id=48415164</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 05 Jun 2026 16:51:44 +0000</pubDate><link>https://github.com/Nayjest/Gito/releases/tag/v4.1.0</link><dc:creator>Nayjest</dc:creator><comments>https://news.ycombinator.com/item?id=48415164</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48415164</guid></item><item><title><![CDATA[New comment by Nayjest in "Tell HN: Litellm 1.82.7 and 1.82.8 on PyPI are compromised"]]></title><description><![CDATA[
<p>Use secure and minimalistic lm-proxy instead:<p><a href="https://github.com/Nayjest/lm-proxy" rel="nofollow">https://github.com/Nayjest/lm-proxy</a><p>```
pip install lm-proxy
```<p>Guys, sorry, as the author of a competing opensource product, I couldn’t resist</p>
]]></description><pubDate>Tue, 24 Mar 2026 20:10:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=47508422</link><dc:creator>Nayjest</dc:creator><comments>https://news.ycombinator.com/item?id=47508422</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47508422</guid></item><item><title><![CDATA[New comment by Nayjest in "[dead]"]]></title><description><![CDATA[
<p>I kept running into the same problem: every time I wanted to try a different LLM provider, I had to rewrite large parts of my code. Different SDKs, different APIs, different response formats. It slowed down experiments and made simple comparisons painful.<p>So I ended up building a small abstraction layer that lets me switch between providers without touching the rest of the app. One interface, multiple backends.<p>In this post, I explain:<p>the exact problem I kept hitting<p>what design choices worked and what didn’t<p>how I structured the abstraction<p>and the trade-offs of this approach<p>If you’ve ever wanted to compare models or avoid vendor lock-in, this might be useful:<p><a href="https://dev.to/chief_yaml_officer/how-i-stopped-rewriting-my-code-every-time-i-switched-llm-providers-4gjh" rel="nofollow">https://dev.to/chief_yaml_officer/how-i-stopped-rewriting-my...</a><p>Source: <a href="https://github.com/Nayjest/lm-proxy" rel="nofollow">https://github.com/Nayjest/lm-proxy</a></p>
]]></description><pubDate>Fri, 06 Feb 2026 15:25:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=46913964</link><dc:creator>Nayjest</dc:creator><comments>https://news.ycombinator.com/item?id=46913964</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46913964</guid></item></channel></rss>