Comparison
Auto claude code research in sleep vs Caveman
Caveman has more GitHub stars (113,046 vs 17,586). Caveman was updated more recently (last commit 2d ago). Data comes straight from GitHub and refreshes daily.
Auto claude code research in sleep
ARIS (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework,…
$
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
Caveman
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
$
/plugin marketplace add JuliusBrussee/caveman| Metric | Auto claude code research in sleep | Caveman |
|---|---|---|
| Type | Agent skill | Agent skill |
| GitHub stars | 17,586 | 113,046 |
| Stars, last 7 days | +55 | +647 |
| Forks | 1,506 | 6,541 |
| Upvotes | 0 | 0 |
| Language | Python | Go |
| License | MIT | Apache-2.0 |
| Last commit | 1w ago | 2d ago |
| Created | Mar 2026 | Apr 2026 |
| Categories | AI & LLM tooling, Docs & writing, Frameworks & SDKs | AI & LLM tooling |