Cache-Pot: AI-native in-memory cache for modern apps

• Cache-Pot is a single-binary, Redis-compatible cache with vector search, semantic caching, and a native MCP server for AI agents.
• It is an in-memory data store built in the Redis mould and reworked for the way AI applications actually use a cache.
• Speaks the Redis wire protocol out of the box, so every client and library you already rely on keeps working without modification.
• Provides vector search, semantic response caching, and a native MCP endpoint for AI agents, all packed into a single self-contained binary.

Key Capabilities:

• Redis Compatibility: Speaks RESP2, the same wire protocol your Redis clients already use. Supports strings, hashes, lists, sets, sorted sets, pub/sub, transactions, and TTLs.
• Vector Search & Semantic Caching: Store and query high-dimensional embeddings with VSET/VSEARCH. Cache model responses by meaning with SCACHE.SET/SCACHE.GET.
• AI Agent Integration: Includes a native Model Context Protocol (MCP) server. Connect Claude or any MCP-compatible agent directly, giving it read, write, search, and memory tools with zero adapter setup.
• Single Binary Deployment: The entire stack—cache, vector store, semantic cache, MCP bridge, and web dashboard—lives in one self-contained binary. No external services, no database, no configuration file required to get started.

Getting Started:

• Install with go install github.com/subh05sus/cache-pot/cmd/cache-pot@latest or use the Docker image.
• Run the binary: cache-pot. It listens for Redis clients on :6379 and opens a web dashboard on :8080.
• Connect any Redis client or redis-cli to localhost:6379.