GitHub Repository

Curated list of AutoResearch use cases with optimization traces and open source implementations

981 stars

Autoresearch, Curated use cases of AutoResearch

Name: Autoresearch, Curated use cases of AutoResearch
Availability: InStock
Author: WecoAI

by WecoAI·Mar 23, 2026·3 points·0 comments

Visit Project View on HN

AI Analysis

●MidDark Horse

Curated list of AutoResearch wins, but it's just a README with links, not a tool.

Strengths

•Documents real results with metrics (53% faster, 18→187 TFLOPS)
•Includes trace links for community verification
•89 stars shows genuine interest in the pattern

Weaknesses

•It's a curated list, not a product or tool with novel technique
•Depends entirely on Karpathy's original AutoResearch prompt

Post Description

It's been 2 weeks since Karpathy released autoresearch. The community is trying to apply it to everything with a measurable metric, here are some successful attempts:

- Shopify's Liquid template engine - 53% faster, 61% fewer allocations - GPU kernels - 18 to 187 TFLOPS - Voice agent prompt engineering - 0.728 to 0.969 eval score - Baseball pitch speed prediction from biomechanics data - Ancient scroll ink detection (Vesuvius Challenge)

We're curating a list of use cases and open-source implementations. PRs welcome, ideally with traces so the community can verify.

URL: https://github.com/WecoAI/awesome-autoresearch