Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: MicroCodex Coding Agent – OpenAI/codex reimplemented in C++ <1MB binary

github.com

Post reply on HN
Print view View original

1–10 of 24 posts

Re: Show HN: MicroCodex Coding Agent – OpenAI/codex reimplemented in C++ <1MB binary

#3

Post by userbinator »

fractorial wrote: post #2

I’m not quite sure why the harness itself needs to be small. Isn’t the system prompt and management of system prompt the bit you want lightweight?

"Why does it need to be large?" should be the question instead.

Re: Show HN: MicroCodex Coding Agent – OpenAI/codex reimplemented in C++ <1MB binary

#5

Post by K0IN »

fractorial wrote: post #2

I’m not quite sure why the harness itself needs to be small. Isn’t the system prompt and management of system prompt the bit you want lightweight?

I think it's nice to have options, but I also don't see the appeal in "sub x mb" (except as codegolf or just for the hacky part, for day to day this does not matter) especially if features are missing or other compromises have been made just for the sake of remaining small.

Re: Show HN: MicroCodex Coding Agent – OpenAI/codex reimplemented in C++ <1MB binary

#6

Post by selcuka »

userbinator wrote: post #3
fractorial wrote: post #2

I’m not quite sure why the harness itself needs to be small. Isn’t the system prompt and management of system prompt the bit you want lightweight?

"Why does it need to be large?" should be the question instead.

A harness needs to be good. Being large is annoying, sure, but it's generally not an issue. Unless this one has feature parity with the "large" ones (hint: it doesn't), I don't see any reason to use it only because it's small.

Re: Show HN: MicroCodex Coding Agent – OpenAI/codex reimplemented in C++ <1MB binary

#7

Post by cyanydeez »

selcuka wrote: post #6
userbinator wrote: post #3

Earlier quoted context omitted.

"Why does it need to be large?" should be the question instead.

A harness needs to be good. Being large is annoying, sure, but it's generally not an issue. Unless this one has feature parity with the "large" ones (hint: it doesn't), I don't see any reason to use it only because it's small.

ultimately, the harness is just going to be another model specifically engineered to be deterministic, like ballbearings in a wheel minimizing friction.

Re: Show HN: MicroCodex Coding Agent – OpenAI/codex reimplemented in C++ <1MB binary

#8

Post by orliesaurus »

i love the idea, but you also need to maintain it long term: in today's world what is the best practice to do that... do you spin up an agent anytime codex-cli updates and mirror the updates in c++ and push a new release? or idk... set up an automated process that does this on a worker on CF in a sandbox when npm updates @openai/codex?

Re: Show HN: MicroCodex Coding Agent – OpenAI/codex reimplemented in C++ <1MB binary

#10

Post by embedding-shape »

fractorial wrote: post #2

I’m not quite sure why the harness itself needs to be small. Isn’t the system prompt and management of system prompt the bit you want lightweight?

Probably you want all of them to be as simple and small as possible, especially if you want to use it to work on itself. Smaller codebases are (generally) easier to work with.
Post reply on HN