Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, retries, circuit breakers, key rotation, singleflight, and Python/TypeScript/Rust parity.

Redis Vector Library (RedisVL) -- the AI-native Java client for Redis.

A KV store built with Aeron, SBE and Agrona. RAFT clustered or single node - fast by default. HTTP, WS & SSE API with JSON payloads. UI, CLI & Embeddable Polyglot Libraries. K8s deployable.

Deterministic LLM caching layer with context optimization, LRU eviction, model-aware token counting, and concurrency-safe request deduplication.

VCAL Core — high-performance semantic cache and vector cache library for LLM applications.

Adaptive semantic cache for LLMs with streaming support, ML-based thresholds, and real-time cost tracking. Built in Rust for sub-millisecond performance.

Something related to LLM caching

Semantic caching layer for LLM calls. Exact-match and embedding-similarity caching with model-version-aware invalidation, use-case segmentation, and cost-saved tracking. Adapters for Redis and DynamoDB.

Reduce LLM API costs and speed up responses by caching completions with NeuroCache’s intelligent, provider-agnostic caching layer.