{"domain":"caveman.so","status":"valid","tier":"listed","authority":47,"verified":false,"title":"Caveman","summary":"Caveman is a token-efficiency stack for AI agents: an open-source output-compression skill (74k+ GitHub stars), a local proxy that compresses eligible context with byte-exact recovery, TypeScript and Python middleware for local tool-result compression, and Caveman Cloud for spend analysis, evaluations, and agent investigations. Teams can connect native LiteLLM traces while keeping their existing inference gateway.","country":null,"country_source":"cdn","publisher_country":null,"publisher_country_source":null,"hosting_country":null,"llms_txt":"https://caveman.so/llms.txt","llms_full_txt":null,"last_checked":"2026-10-25T23:47:52.396Z","agent_terms":null,"categories":["ai-ml"],"capabilities":[],"inferred_tags":[],"audience":null,"agent_uses":[],"language":null,"platform_generated":null,"agent_summary":null,"llms_txt_cached":"https://agentwebmap.com/v1/domain/caveman.so/llms.txt","agentic":"documentation","section_keys":["caveman-products","company","comparisons-and-switching-guides","documentation","guides","how-an-agent-calls-caveman","legal","machine-readable-endpoints","models","optional","products","products-caveman","read","related","when-to-use-caveman"],"section_partial":true,"section_indexed_at":"2026-10-25T23:47:55.828Z"}