fveiras

Semantic and intent-based memory for AI SDK. Supports one-shot semantic caching and multi-turn intent-aware conversations. Reduces token costs by reusing similar responses.

Semantic caching layer for AI SDK. Automatically generates embeddings for prompts, stores them in Upstash Vector and Redis, and reuses semantically similar responses to reduce token costs.

Multi-provider AI agent framework for Model Context Protocol (MCP) servers