redis-developer

Typed wrapper for Redis LangCache (managed semantic cache) with singleton pattern and a generic search/set/delete/flush interface. Use when the user needs semantic caching of LLM/agent responses.

Typed wrapper for Redis Context Surfaces (surface CRUD, MCP tool calling, record loading). Use when working with Context Surfaces, structured data tools, or MCP-based AI agent integrations.

Zero-boilerplate Express API server with built-in security (helmet, CORS, rate limiting, compression), structured error handling, request-id child loggers, and graceful shutdown. Use when the user needs an API server with minimal setup.

Fast, multi-transport structured logger (console, file, MongoDB, SQL). Built on Pino with a class-based Logger exposing static factory and singleton methods. Use when the user needs logging with any combination of console, file, MongoDB, or relational database output.

Typed MongoDB CRUD utility with Zod validation, auto-managed fields, soft deletes, and optimistic concurrency. Use when the application needs a MongoDB data layer.

Typed wrapper for Redis Agent Memory Server (working memory, long-term memory, summary views, memory prompt, lifecycle). Use when the user needs agent memory management via the Redis Agent Memory Server REST API.

Typed Redis client wrapper with singleton pattern, structured logging, and getClient() escape hatch. Use when the user needs Redis connectivity with string, JSON, hash, key management, pipeline, or pub/sub operations.

Redis backends for Google's Agent Development Kit (ADK). Use this skill when the user wants to back an ADK agent with Redis: persistent sessions and long-term memory via Redis Agent Memory Server, RAG search tools over a RedisVL index (vector / hybrid / range / text / SQL), MCP toolsets for RedisVL or Agent Memory Server, or semantic caching for LLM responses and tool results.

Run the full CI gate locally (format, lint, typecheck, test, bundle) and verify the committed dist/ is in sync before committing or opening a PR. Use whenever you've changed src/ and are about to commit, push, or open a PR — or when CI's "Check dist/" or "Continuous Integration" jobs are failing and you need to reproduce them locally.

Iris is Redis's umbrella for AI-focused products. Use this skill when integrating with the Iris Redis Agent Memory (RAM) data plane on Redis Cloud — recording session events for an AI agent, creating or searching long-term memories, configuring a memory store, or tuning background memory promotion. Code examples use the official `redis-agent-memory` (Python) and `@redis-iris/agent-memory` (TypeScript) SDKs.

Redis performance optimization and best practices. Use this skill when working with Redis data structures, Redis Query Engine (RQE), vector search with RedisVL, semantic caching with LangCache, or optimizing Redis performance.