Hello HN! We're building a caching solution for LLMs (ChatGPT, Claude). By combining cutting-edge approaches, such as edge computing, prompt compression, vectorization, and others - it can reduce your AI bills by up to 10x and significantly lower response times. Key Features: - cost efficiency: our system stores frequent queries, reducing the number of upstream (paid) API calls - fast responses: with various nodes globally, we reduce latency by serving data from the nearest location - scalability: designed to handle increasing loads and data sizes without degrading performance. The cache operates transparently, requiring minimal changes to your existing setup. It's like your local content delivery network (CDN), but for LLMs, ensuring that users get the fastest possible access to information. While still in its early stages, we are excited about the potential and are looking to gather feedback from the community. We will share the demo once you subscribe to our mailing list (to control our spending ;)) This could be a game-changer for those using LLMs in prod environments where cost and response time are critical. We’re eager to hear what you think! (launching from the Bunny Coworking House in SF - thanks, Henry, Liyen, and Grace, for having us) |