llm-response-cache vs lru-tokens vs tool-result-cache

In-memory LRU cache for LLM responses keyed by request hash

LRU cache where eviction is weighted by token count, not entry count. Bound a prompt cache by tokens (or any other size unit) instead of N entries. Zero deps.

Content-addressable LRU cache for LLM agent tool calls. Same tool, same args -> same answer, returned from memory. Optional TTL, content-addressable on (tool_name, args) with canonical-JSON keys.