Cache Semantic Kernel in your research assistant with Crowkis
Building research assistants on Semantic Kernel? Add a semantic cache so overlapping literature and summary questions stop costing full price.
Research assistants built on Semantic Kernel share one problem: overlapping literature and summary questions. Each repeat is a full-price Semantic Kernel call for an answer you already have.
Put a semantic cache in front. Point Semantic Kernel's base URL at the Crowkis OpenAI-compatible gateway, or wrap the call in get-or-compute, and reworded repeats are served from cache, no rewrite of your research assistants logic.
base_url = "http://127.0.0.1:6380/v1" # Crowkis gateway, semantic cache in front
On repetitive traffic this cuts costs up to 60-70% on repetitive workloads, and every hit carries a confidence score so reuse stays safe. Community edition ships at full power, free to run.