node-fetch with caching.

Provider-agnostic LLM access runtime SDK for Sentropic.

- Supports redis cache for `@envelop/response-cache` plugin - Suitable for serverless deployments where the LRU In-Memory Cache is not possible

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

Daemon that manages the @vltpkg/cache disk store

Zero-dependency LLM response cache with exact, fuzzy (Jaccard), semantic (HNSW cosine) matching, Redis/SQLite/FS/Memory backends, MCP server, HTTP middleware, streaming, analytics, and local embeddings.

Serve static files

Rush plugin for generic HTTP cloud build cache

Better streaming static file server with Range and conditional-GET support

Require hook for automatic V8 compile cache persistence

OCSP Stapling implementation

Cache-control header utility that parses human readable time strings into seconds.

An ultra-simplified API response caching middleware for Express/Node using plain-english durations.

Require hook for automatic V8 compile cache persistence

LLM capture proxy with Anthropic cache_control TTL stamping, vision handoff, concurrency gating, rate limiting, and a live inspection dashboard

Model selection: the /model popupSelect over session.models / session.selectModel

Decompress a HTTP response if needed

the http/https agent used by the npm cli

LLM-agnostic AI platform for SAP CAP. 11 providers behind one API (Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Ollama, Groq, Fireworks, DeepSeek, Mistral, OpenAI-compatible, SAP Generative AI Hub) with 30+ middleware primitives spanning cost/resi

LRU and FIFO caches for Client or Server