petals vs caveman

A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.

petalscaveman
TaglineRun LLMs at home, BitTorrent-styleCuts 65% of tokens in AI coding agent responses.
Stars10k86k
Forks6214.8k
Open issues112370
LanguagePythonJavaScript
LicenseMITMIT
Last pushedSep 7, 2024Jul 3, 2026
CategoriesLLM Frameworks, Inference & ServingDeveloper 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