GIT_FEED

rduffyuk/engineering-memory-benchmark

Empirical study: layered retrieval (typed→semantic→grep) scores 0.954 for LLM-generated engineering artifacts. 5 conditions, 3 model tiers, 36 generated ADRs, 23 score files.

View on GitHub
0Active

On the radar — signal detected

Stars
3
Forks
0
Contributors
0
Language
Python

Score updated Jun 26, 2026

// SUBSCRIBE

The repos that moved this week, why they matter, and what to watch next. One email. No noise.