petals vs caveman
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| petals | caveman | |
|---|---|---|
| Tagline | Run LLMs at home, BitTorrent-style | Cuts 65% of tokens in AI coding agent responses. |
| Stars | 10k | 86k |
| Forks | 621 | 4.8k |
| Open issues | 112 | 370 |
| Language | Python | JavaScript |
| License | MIT | MIT |
| Last pushed | Sep 7, 2024 | Jul 3, 2026 |
| Categories | LLM Frameworks, Inference & Serving | Developer Tools, LLM Frameworks |
petals
Petals enables running and fine-tuning large language models locally with distributed computing techniques, offering up to 10x faster performance compared to offloading tasks.
Python
caveman
A skill/plugin for various AI agents, including Claude Code and other platforms, reducing output tokens for more concise, direct communication while maintaining accuracy.
JavaScript