Prompt-hash-keyed LLM response cache with model-aware invalidation

> Redis-backed LLM response cache for `@llm-optimize/core`. Share cached responses across multiple servers, workers, or serverless functions.

> In-process LLM response cache for `@llm-optimize/core`. Zero dependencies, TTL support, and configurable max size with automatic eviction.

Semantic LLM response cache for @theokit/sdk — vector + FTS hybrid lookup, in-memory + JSON file stores, plugin integration.

Parses Cache-Control and other headers. Helps building correct HTTP caches and proxies

Similarity-based (semantic) LLM response cache for NodeLLMCache

HTTP response freshness testing

Apollo Server full query response cache

No description provided.

Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

- Skip the execution phase and reduce server load by caching execution results in-memory. - Customize cache entry time to live based on fields and types within the execution result. - Automatically invalidate the cache based on mutation selection sets. -

fresh rewrite in TypeScript with ESM targets

First-message LLM provider plugin for DeepSeek Harness session titles

Composable caching primitives with TTL, SWR, and HTTP response caching

Middleware to destroy caching

A cache object that deletes the least-recently-used items.

Cache polyfill for the ServiceWorker

Fetch package artifacts and metadata from registries

A lightweight cache for file metadata, ideal for processes that work on a specific set of files and only need to reprocess files that have changed since the last run

Detox driver for Wix Pilot usage