Tag
The article describes how building an intelligent caching gateway (Hawiyat Composer) saved significant AI API costs by eliminating repeated token waste through exact-match caching, semantic caching, model routing, and local routing.
Building an open-source API gateway for agentic AI workflows that provides visualization of multi-LLM and tool calls, tracking tokens, cost, and latency without requiring code instrumentation. Uses Rust and Go servers with a Python correlator, seeking collaborators and feedback from AI ops users.
The author shares how running multiple persistent AI agent profiles under Hermes led to high API costs, solved by implementing tiered model policies per profile, pre-processing inputs, and using an API gateway for cost visibility, reducing daily costs from $14-18 to $7-10.
OpenWA is a free, open-source WhatsApp API Gateway with a pluggable architecture, multi-session support, Docker deployment, and a full React dashboard, giving developers full control over their messaging infrastructure without vendor lock-in.