oMLX is a high-performance local LLM inference server optimized specifically for Apple Silicon Macs. Built on the MLX framework, it supports text LLMs, VLMs, OCR, and embedding models. It features a unique Tiered KV Cache system (Hot RAM + Cold SSD) that persists context across requests and server restarts, making it ideal for coding agents like Claude Code. oMLX provides a native macOS menubar app and a web dashboard, supporting continuous batching, automated memory management via LRU eviction, and seamless MCP integration.
SwiftClaw is an AI Agent product meticulously optimized for the Apple ecosystem. It harnesses the exceptional performance and power efficiency of native Apple Silicon chips, combined with the robust capabilities of the CoreML framework, to deliver a highly efficient and fluid on-device AI experience for developers and end-users. SwiftClaw is designed for low-latency, high-throughput machine learning inference, enabling complex AI functionalities to run locally on Mac, iPad, and iPhone devices without cloud dependency. Its core strength lies in ultimate localized processing and seamless integration with the Apple hardware-software stack, providing a solid foundation for intelligent applications, data analysis, personalized services, and innovative AI solutions, particularly ideal for edge computing scenarios demanding stringent performance and privacy.