Show HN: Run Claude Code CLI with Azure&open source LLMs saving costs (github.com)

A new CLI tool, Lynkr, has been unveiled, enabling Claude Code CLI to seamlessly connect with various non-Anthropic backends, while also providing robust management for local tools and Model Context Protocol (MCP) servers. This tool is significant for the AI/ML community as it not only enhances flexibility by supporting multiple providers like Databricks, Azure-hosted Anthropic endpoints, and OpenRouter, but also optimizes costs by allowing users to choose the most suitable models for their specific needs, including local and cloud options. Lynkr boasts a production-ready architecture with 14 hardening features designed for reliability and performance, achieving an impressive throughput of 140,000 requests per second with minimal latency. It includes advanced enterprise observability tools, real-time metrics, and intelligent routing logic for optimal cost efficiency. The integration of features such as prompt caching, policy enforcement, and workspace awareness, along with comprehensive logging and error handling mechanisms, affirms Lynkr's potential to meet the demands of enterprise-level AI applications. This innovative tool not only parallels Anthropic's Claude ergonomics but also delivers enterprise-grade reliability and functionality that could redefine how developers interact with AI models.