Building My-Starred-Repos - 813 Stars, Auto-Updated Daily
I star repos I'll never look at again. So I built a tracker that curates 813 of them — AI agents, dev tools, systems, LLMs, web dev — searchable, filterable, auto-updated daily.
I star repos I'll never look at again. Everyone does. The star list is a graveyard — no signal, no order, just accumulated intent.
I built My-Starred-Repos to fix that. 813 curated GitHub starred repos — AI agents, dev tools, systems, LLMs, web dev. Search, filter, explore. Auto-updated daily.
What it is
A PWA tracker that turns my star hoard into a searchable index. GitHub Actions runs daily, pulls the starred list, and rebuilds the site. Python handles the sync, the frontend is plain HTML/CSS/JS, the whole thing is a PWA you can install.
The problem it solves
Stars are hoarding until something curates them. The difference between a star list and a resource is search, filters, and freshness. This has all three — and the daily Action keeps it honest.
Why Python + Actions
The sync is a cron job with a GitHub token. No server to babysit, no database — the daily run regenerates the whole site. Cheap to run, always current.
What's next
Better dedup across categories. More granular filters. Maybe a "forgotten gems" pass that surfaces old stars nobody looks at.
Stars are hoarding until something curates them.
More Essays
Building jev-curate: Fast Synthetic Dataset Sifter in Rust
Filtering synthetic training data with TypeSafe AI Jev: streaming JSONL and Parquet rows through calibrated System One gates at 70ms latency with zero memory accumulation. � 5 min
systemsBuilding jev-git: Sub-Second Git Reflex Gate in Rust
Screening staged git diffs for leaked secrets, destructive payloads, and AI hallucinations in 80ms using TypeSafe AI Jev System One. � 4 min
systemsBuilding jev-scout: Zero-Hallucination Crate and Repo Scout
Preventing AI package hallucinations: discovering real crates and GitHub repositories using live registry APIs and TypeSafe Jev speculative fan-out scoring. � 4 min