Yesterday I wrote a new coding agent

I thought it would be interesting to see how small I could get a working terminal based coding agent.

So I booted up Codex CLI and started throwing prompts.

The result is this:

github.com

GitHub - merefield/codegollm: Minimalistic Go based CLI coding agent a la mode

Minimalistic Go based CLI coding agent a la mode

This is a fully working coding agent, much like Codex CLI. (but of course I’m sure far less capable, even if surprisingly so in its own way)

Built with Go so it doesn’t take a year to compile and yet performs super fast.

It works with OpenAI API and Ollama.

It can:

• read, write, edit and run arbitrary bash commands
• it presents code deltas and commands for you to review and approve
• it maintains an evolving context summary beyond the last X interactions so it uses tokens more efficiently
• it maintains a session for the current working directory
• it is guardrailed to the current directory (best efforts!)
• you can interrupt the agent and set it off in a different direction

I think the fun stat here is the number of lines of code, using CodeGollm as a baseline:

• Codex repo is 250x bigger
• Pi-mono coding agent (known for its small size) is 7x bigger

What I learnt doing this is:

• The fundamentals of all this remain pretty straightforward.
• Codex CLI will happily build you something you can replace it with
• Model size really matters - Gemma 4 was a disaster, but gpt-4.1-mini can code pretty well, despite not racking up internal reasoning!

You probably won’t be using this because of course I can’t build something to compete with Codex CLI in a day and there is no ChatGPT auth, but I thought it interesting to share … have fun building!