Weco

CLI that iteratively optimizes your code against a measurable evaluation metric.

Desktopfreemiumglobal

Weco is a CLI that uses an LLM-guided tree search to iteratively optimize code, prompts, or agent harnesses against a measurable evaluation metric you define, automatically applying changes and re-running your evaluation script. It's aimed at ML engineers and developers optimizing things like model accuracy, prompt quality, or GPU kernel performance, with a dashboard for tracking both its own runs and externally-run optimization loops.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Weco - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Weco to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Weco (or something else) actually fits.

Try a problem