Redis Semantic Cache

This wraps Redis Cloud's LangCache preview service so you can cache LLM responses by semantic similarity instead of exact string match. When a prompt comes in, it searches for similar embeddings and returns the cached answer if the cosine distance clears your threshold, skipping the model call entirely. Start at 0.9 for the threshold, crank it to 0.95+ if wrong answers hurt, or drop to 0.8 for looser matching on internal tools. The big gotcha is keeping task types separate. Don't let support queries and code questions share a cache or you'll serve nonsense. Split by cache ID or filter with custom attributes if you need finer isolation within one instance.

Install to Claude Code

npx -y skills add redis/agent-skills --skill redis-semantic-cache --agent claude-code