Unified client SDK for KB Labs platform. Zero dependencies. Access LLM, Cache, VectorStore, Analytics, and any adapter through a single client.

HTTP service wrapper for llm-cache

Qdrant vector database adapter for llm-cache semantic search

Observability, metrics, logging, and tracing for llm-cache

Cost tracking and pricing calculations for llm-cache

Redis storage adapter for llm-cache

DynamoDB storage adapter for llm-cache

Core caching engine for llm-cache — semantic and exact-match caching with embedding-based similarity

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

Local-only, zero-dependency byte-exact caching reverse proxy for the Anthropic Messages API. Replays cached responses with no upstream call on exact-match repeats.

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

Require hook for automatic V8 compile cache persistence

A simple key/value storage using files to persist the data

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

Require hook for automatic V8 compile cache persistence

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

A semantic cache for LLM API calls using local embeddings and vector similarity

TypeScript definitions for http-cache-semantics

LRU and FIFO caches for Client or Server

[](https://www.npmjs.com/package/@aws-sdk/endpoint-cache) [](https://www.npmjs.com/package/@aws-sdk/e