Minimalistic AI Harness in 62 lines of bash script

Description and use

<p>In this article, we'll build a minimalist AI harness step by step, from a simple individual LLM call to a chatbot to a coding agent that can build a game like Tetris. Using nothing but Bash script.</p> <p>All the source code is available at <a href="https://github.com/antonum/bash-harness" rel="noopener noreferrer">https://github.com/antonum/bash-harness</a></p> <p>What you'll need:</p> <ul> <li>Access to LLM. I'm using OpenAI's LLM via OpenRouter here. But you can use any other modern LLM capable of tool calling, either locally or remotely</li> <li>API_KEY for your LLM provider</li> <li>Co

Problem

<p>In this article, we'll build a minimalist AI harness step by step, from a simple individual LLM call to a chatbot to a coding agent that can build a game like Tetris. Using nothing but Bash script.</p> <p>All the source code is available at <a href="https://github.com/antonum/bash-harness" rel="noopener noreferrer">https://github.com/antonum/bash-harness</a></p> <p>What you'll need:</p> <ul> <li>Access to LLM. I'm using OpenAI's LLM via OpenRouter here. But you can use any other modern LLM capable of tool calling, either locally or remotely</li> <li>API_KEY for your LLM provider</li> <li>Co

Outcome

<p>In this article, we'll build a minimalist AI harness step by step, from a simple individual LLM call to a chatbot to a coding agent that can build a game like Tetris. Using nothing but Bash script.</p> <p>All the source code is available at <a href="https://github.com/antonum/bash-harness" rel="noopener noreferrer">https://github.com/antonum/bash-harness</a></p> <p>What you'll need:</p> <ul> <li>Access to LLM. I'm using OpenAI's LLM via OpenRouter here. But you can use any other modern LLM capable of tool calling, either locally or remotely</li> <li>API_KEY for your LLM provider</li> <li>Co

Evidence

Minimalistic AI Harness in 62 lines of bash script

Source