> The main LLM optimization middleware for TypeScript apps. Reduces token usage, cuts API costs, protects sensitive data, caches responses, and retries failures — all in one `chat()` call.

offline & partial name search in caches for npm

Isolate Vite optimizer caches by Astro command so concurrent workflows do not interfere.

> Types and utilities for building custom plugins for `@llm-optimize/core`. Hook into the request pipeline, register custom middleware, routers, caches, and analytics sinks.

OpenCode plugin that watches your task context, searches 7 skill marketplaces, caches locally with FTS5, and auto-recommends relevant skills.

Flexible file and memory caches

Sanvika Cache SDK — HTTP client for cache.sanvikaproduction.com + localStorage (web) + AsyncStorage (React Native) client caches

Interactive Clack CLI to prune Next.js build artifacts and caches to free disk space

Embeddable web UI for inspecting in-process memory caches (and Redis) in Node.js services

Caches the result of following loaders on disk.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

The sw-builder package automates the creation of your Application's Service Worker, which pre-caches your build. This leads to a better overall performance and enables users to access your PWA without an Internet connection.

MCP proxy that lazy-loads and caches tool schemas to reduce context token overhead by 6-7x (verified)

Brandfine consumer SDK — typed HTTP client, server-side caches, locale + navigation resolvers, and webhook helpers for landing-page integrations.

Run GitHub Actions locally — pause on failure, retry in place, and keep caches on your machine.

sequelize plugin that caches find* responses

A benchmark harness for JavaScript/TypeScript caches: hit-ratio miss-ratio curves against Belady's OPT and throughput with confidence intervals, across standard synthetic workloads and real traces, with markdown tables and SVG charts. Reference policies (

Memoization decorator that caches function results based on arguments. Returns cached results for subsequent calls with the same arguments.

MCP server for inspecting and operating @leejpsd/nextjs-cache-handler Redis caches — health, key inspection, tag state, SWR simulation, and dry-run-first invalidation for AI agents.

Filter for wFiles provider's that caches file stats, names and records.