Descripción
One command wraps Claude Code, Codex, Hermes, and more with a local proxy that compresses logs, tool output, and files before every provider call. In a pinned 54-run benchmark: 33.2% fewer input tokens with 18/18 correctness checks. Caveman can also run any existing agent skill with ~70% fewer tokens by loading text as images. Built on an open-source ecosystem with 97K+ GitHub stars.
Descripción
One command wraps Claude Code, Codex, Hermes, and more with a local proxy that compresses logs, tool output, and files before every provider call. In a pinned 54-run benchmark: 33.2% fewer input tokens with 18/18 correctness checks. Caveman can also run any existing agent skill with ~70% fewer tokens by loading text as images. Built on an open-source ecosystem with 97K+ GitHub stars.
Preguntas frecuentes
¿Qué es Caveman?
One command wraps Claude Code, Codex, Hermes, and more with a local proxy that compresses logs, tool output, and files before every provider call. In a pinned 54-run benchmark: 33.2% fewer input tokens with 18/18 correctness checks. Caveman can also run any existing agent skill with ~70% fewer tokens by loading text as images. Built on an open-source ecosystem with 97K+ GitHub stars.
¿Caveman es gratis?
Sí, Caveman ofrece un plan gratuito.
¿Qué puede hacer Caveman?
One command wraps Claude Code, Codex, Hermes, and more with a local proxy that compresses logs, tool output, and files before every provider call. In a pinned 54-run benchmark: 33.2% fewer input tokens with 18/18 correctness checks. Caveman can also run any existing agent skill with ~70% fewer tokens by loading text as images. Built on an open-source ecosystem with 97K+ GitHub stars.
Redes sociales
Usar herramientaReseñas
Aún no hay reseñas. Sé el primero en compartir tu experiencia.
Herramientas patrocinadas
Herramientas recomendadas
Mantente al día con las últimas herramientas de IA
Obtén las últimas novedades, únete a nuestro boletín
Leído y confiado por 50,000+ lectores
































