ykachala/semantic-cache

Embedding-similarity response cache for LLM calls. Serve a cached answer when a new prompt is semantically close to a previous one — cutting cost and latency.

dev-main 2026-06-01 23:48 UTC

Requires

• php: >=8.3
• psr/log: ^3.0
• psr/simple-cache: ^3.0

Requires (Dev)

• friendsofphp/php-cs-fixer: ^3.0
• phpstan/phpstan: ^2.0
• phpunit/phpunit: ^11.0

Suggests

• ext-pdo: Required for the pgvector store
• predis/predis: Required for the Redis vector store
• ykachala/meter: Measure exactly how much spend the cache is saving you

MIT

• redis
• cache
• semantic
• vector
• ai
• latency
• llm
• embeddings
• qdrant
• pgvector
• cost-optimization