MindGods5d ago

Components of a Coding Agent

https://magazine.sebastianraschka.com/p/components-of-a-coding-agent

Components of A Coding Agent

How coding agents use tools, memory, and repo context to make LLMs work better in practice

Ahead of AI
Show threadarmcat5d ago
I still find it incredible at the power that was unleashed by surrounding an LLM with a simple state machine, and giving it access to bash
Show threadstanleykm5d ago
unfortunately all the agent cli makers have decided that simply giving it access to bash is not enough. instead we need to jam every possible functionality we can imagine into a javascript “TUI”.
Show threadHarHarVeryFunny

If all you want is a program that calls the model in a loop and offers a bash tool, then ask Claude Code to build that. You won't like it though!

For a preview of what it'd be like, just tell your AI chat app that you'll run bash commands for it, and please change the app in your "current directory" to "sort the output before printing it", or some such request.

Apr 4 at 5:12pmWeb
Show threadYokohiii5d ago
I think you get him wrong? He is already concerned about "bash on steroids" and current tools add concerning amounts of steroids to everything.
Show threadstanleykm5d ago
i did.. and thats what i use. obviously its a little more than just a tool that calls bash but it is considerably less than whatever they are doing in coding agents now.
Show threadsenko5d ago

Claude Code with Opus 4.6 regularly uses sed for multi-line edits, in my experience. On top of it, Pi is famously only exposing 4 tools, which is not just Bash, but far more constrained than CCs 57 or so tools.

So, yes, it can work.