<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: kamaludu</title><link>https://news.ycombinator.com/user?id=kamaludu</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 30 Jun 2026 20:21:03 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=kamaludu" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>Nice! your project use smaller components (do one thing and do it well), bash4llm is more monolithic because I focus Bash-only portability and security.
different approach for similar ideas, I see your repo, thank you!</p>
]]></description><pubDate>Tue, 30 Jun 2026 17:40:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=48736289</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48736289</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48736289</guid></item><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>English idioms are hard for me (I'm Italian), so I can misunderstand your point.
bash4llm is long because it uses pure Bash, and making Bash-only reasonably safe and consistent for LLM calls it's difficult. For me, that's exactly what I like in the project.</p>
]]></description><pubDate>Tue, 30 Jun 2026 15:39:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=48734302</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48734302</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48734302</guid></item><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>I've applied a set of corrections, on Bash4LLM core, to reduce redundancy and make the flow more deterministic. Optimized safe_mkdir to eliminate superfluous calls to chmod, simplify temp file management by removing a redundant pre‑validation, remove repeated controls on ensure_run_tmpdir, unified internal standards but with  backward compatibility, to correct duplications on providers management caused by a second redundant scan of provider modules, preserved diagnostic mode (CLI and environment variables).
These are small jobs, but useful for clean and consistent runtime.</p>
]]></description><pubDate>Mon, 29 Jun 2026 15:59:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=48720986</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48720986</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48720986</guid></item><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>Thank you very much for your attention and for your time.
The problems that you have seen are real.
Inspired by your feedback, I proceed to work on it, and I will fix the hollow redundancies and the bad duplications.</p>
]]></description><pubDate>Mon, 29 Jun 2026 12:44:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=48718551</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48718551</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48718551</guid></item><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>I don't think it is of poor quality.
I post this because I wish it is good for others.
It's not auto generated, I made this.</p>
]]></description><pubDate>Mon, 29 Jun 2026 00:02:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=48713118</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48713118</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48713118</guid></item><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>I don't think , I can pay if it's really good for this work, but I've seen the characteristics of pay plan and are not really better for my use case.
The free plan is not the reason for the code size; the architecture is the reason.
the best choice for me, for this work, is to have a real AI (not a toy installed on a laptop) without limitations and filters, but for this need many tens of thousands of €</p>
]]></description><pubDate>Sun, 28 Jun 2026 23:23:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=48712843</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48712843</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48712843</guid></item><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>I work with termux on Android, and it works fine.
For now, I've not tested bash4llm on other environments, but I think it does work because the required packages are the minimum common denominator for all environments, ad with this requirements installed it should work on bsd-like too.
I tried python too, at the start, and it was too slow.</p>
]]></description><pubDate>Sun, 28 Jun 2026 23:03:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48712685</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48712685</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48712685</guid></item><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>The macro sections/sections/sub-sections in the code are not random, I intentionally decide that.
In brief:
PRECORE_BOOT - for initialization
PRECORE_RUN - persistency, history, cache
PROVIDER - embedded provider (groq)
CORE_SETUP - global runtime configuration, parsing parameters, LLM whitelist, user configuration 
CORE_PROVIDER - providers validation, prompt assembly, chat sessions, models tuning<p>The macro sections has two functions:
1, for me, to navigate the code
2, for LLMs, to understand my structure<p>The project does many things, so i need a clear sections structure to separate responsibilities.<p>You can see more information on the documentation, but the architectural spec is only in Italian.</p>
]]></description><pubDate>Sun, 28 Jun 2026 22:48:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=48712553</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48712553</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48712553</guid></item><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>Architecture and structure are my decisions, LLM are instruments, simple executors, today i think are commonly used.
Write code with LLM is not "push a button", it's a technical way of work, needs study and practice.
5k lines are months of work, debug, refactor, testing.
5k lines are the result of a long (and difficult) work, but LLM helps your productivity.
The most important thing, for the humans, are the architectural decisions, and understanding how your current LLM reasoning and behavior.
I decide architecture and structure; LLM only writes code (that need debug and testing), LLM are executors, not automatic.
LLM are only software, and are new instruments to learn.
Important thing: I use only free plan, of LLMs that have a real free plan.</p>
]]></description><pubDate>Sun, 28 Jun 2026 22:17:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=48712302</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48712302</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48712302</guid></item><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>Yes, the code is big and bulky, i know.
But i am a single person, not a team.
I write simple and clear for me, because i need to mantain it.
Only Bash, zero dependencies, i like this.<p>thank you for your comment!</p>
]]></description><pubDate>Sun, 28 Jun 2026 20:44:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=48711453</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48711453</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48711453</guid></item><item><title><![CDATA[New comment by kamaludu in "Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs"]]></title><description><![CDATA[
<p>well, i write Bash4LLM to be:<p>. Portable - You need only: bash, coreutils, findutils, util-linux, gawk, curl, jq.
  No Python (slow), no Node (heavy), no Golang (need too many binaries, one for each OS, hard to maintain for one single person like me).<p>. Single file - only one. I write many extras, but all are optional.<p>. Idempotent - you copy it where you want and go!<p>. Transparent - open the file and read.<p>. Extras for all, and all optional: help file, extra providers, improved session engine,
  small GUI/CGI, etc...<p>Default (embedded) provider is Groq, because when I start the project, was the best free API service for AI.<p>I'm ready to answer to your question... with my terrible english...<p>Cristian (kamaludu)</p>
]]></description><pubDate>Sun, 28 Jun 2026 20:36:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=48711369</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48711369</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48711369</guid></item><item><title><![CDATA[Show HN: Bash4LLM+ – A lightweight, dependency-free Bash wrapper for LLM APIs]]></title><description><![CDATA[
<p>Bash4LLM is a single-file Bash wrapper for interacting with LLMs from the terminal.  I created it because I wanted something simple that worked without installing Python, Node, or any other runtime.<p>It uses only Bash, curl, and jq. You can send prompts, start a small chat, process files line by line, stream output, and save session metadata in JSON format.<p>I tried to make it safe and predictable: no use of the system /tmp, no use of eval. Groq is supported by default, and other providers can be added with dedicated Bash scripts in the extras/providers/ folder.<p>Example:<p><pre><code>  echo "explains the command: ls -l" | ./bash4llm</code></pre></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48710827">https://news.ycombinator.com/item?id=48710827</a></p>
<p>Points: 59</p>
<p># Comments: 22</p>
]]></description><pubDate>Sun, 28 Jun 2026 19:43:10 +0000</pubDate><link>https://github.com/kamaludu/bash4llm/</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=48710827</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48710827</guid></item><item><title><![CDATA[Show HN: GroqBash – Single‑File Bash Client for Groq API]]></title><description><![CDATA[
<p>I built GroqBash, a single‑file Bash client for the Groq API (OpenAI‑compatible).
I wanted something fully auditable, with no dependencies, and that worked reliably on Termux, where /tmp isn’t writable.
Everything lives inside a self‑created groqbash.d directory, and the core script avoids eval, avoids /tmp, and keeps permissions strict.<p>The project now includes optional extras: additional providers (including Gemini), extended documentation, small security tools, and a tiny test suite.
The core stays minimal and portable; extras are opt‑in.<p>I’d love to get:
- feedback on the design and Bash choices
- visibility to see if others find this useful
- testing on different environments (Linux distros, macOS, WSL, Termux)<p>Repo: <a href="https://github.com/kamaludu/groqbash" rel="nofollow">https://github.com/kamaludu/groqbash</a><p>Note: I’m not a native English speaker. I read English fairly well, but I usually rely on automatic translators (and sometimes GroqBash itself) when writing.
Happy to clarify anything if needed.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46759974">https://news.ycombinator.com/item?id=46759974</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 25 Jan 2026 23:52:56 +0000</pubDate><link>https://github.com/kamaludu/groqbash</link><dc:creator>kamaludu</dc:creator><comments>https://news.ycombinator.com/item?id=46759974</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46759974</guid></item></channel></rss>