A Semantic cache built on top of Upstash Vector DB

Intelligent AI Gateway for IDEs & Agents — Semantic cache, Privacy Firewall, Infrastructure Command Center, and Autonomous Cost-Optimization.

Valkey-native semantic cache for LLM applications with built-in OpenTelemetry and Prometheus instrumentation

Fact-Checker MCP Server - SENSE + GATE verification service with semantic cache

Production caching seam for AI workloads (keyless/offline memory reference + Redis adapter): exact-match cache, verified semantic cache, embedding cache, singleflight request coalescing, negative cache, and epoch-based invalidation. Makes the gateway + RA

Self-hosted semantic cache using local embeddings

One install for the BetterDB AI stack on Valkey: agent cache, semantic cache, retrieval, agent memory, and search helpers

Pro RAG chatbot plugin — DOCX/TXT/MD/CSV + website crawl, client dashboard, citations, semantic cache. Requires a paid license key (acetrum.com) to function; degrades to a free-tier subset without one.

useMemo and useCallback but with a stable cache

Ultra-fast, zero-dependency local semantic cache for LLM/AI prompt responses with built-in TF-IDF vectorizer, vector similarity search, and file persistence.

Caching mock fetch implementation for all runtimes and frameworks.

Stable semantic cache keys for AI prompts, tools, models, and retrieval context.

Fact-Checker MCP Server - SENSE + GATE verification service with semantic cache

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

TypeScript-native semantic cache for LLM responses (OpenAI/Anthropic/Google). Sub-millisecond exact-match plus an optional zero-API-key semantic layer that serves paraphrased prompts. Memory or Redis.

OpenTelemetry semantic conventions

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

Cut LLM API costs 60–90% in 3 lines of code. Semantic cache with BM25+ fuzzy matching, persistent sessions, AI memory adapter. Works with OpenAI, Anthropic, LangChain, Vercel AI SDK. No embeddings required for basic caching.

Require Node module and immediately remove it from module cache to force loading again next time

Official TypeScript client for Sulci — the context-aware semantic cache for LLM apps. Fail-open by default.