Andy

@dev-bre

Commit activity

7 commits in the last year

longest streak 2 days

267 / 400 XP133 XP to maintainer

Mon, Oct 19

Running local LLMs is not going to replace your Claude or Codex subscription.. for now. You are running local LLMs to get ready for a technological shift which is already happening. Local models are at level with previous generation frontier models. Qwen4.8 27B model + Hermes…
I am running it locally because Claude and others are censored. I want to test Reverse Engineer Anything. Works only with uncensored models. Or in my case the local model is not working because some misconfig in opencode or something else, idk.
I think it is already possible or it should be possible, to route an agent to either a cloud model or local model based on the effort/complexity of the task. But I also hope that soon running local models will get a bit more affordable, right now is quite expensive.

Sun, Oct 18

@nunomaduro I think it would be nice to allow ppl to star their own content. I don’t see a reason to prevent this and in general others are more inclined to star others content if they are not the first.

That's @dev-bre's root commit.