Show HN: Tokdash – a local dashboard for AI token and quota tracking (github.com)

Tokdash has launched a new local token and cost dashboard designed for AI coding tools, significantly enhancing performance and usability. This tool operates approximately 30 times faster than previous versions in cold usage scans and 15 times faster than comparable local benchmarks. It allows users to retain their history of interactions with AI tools, offering seamless tracking of token usage and quotas for services such as Codex and Claude Code. The dashboard can be tried directly via its demo site without installation, making it accessible for many developers. This development is significant for the AI/ML community as it provides precise breakdowns of token usage, including input, output, and cache metrics, while prioritizing user privacy and data security. The dashboard introduces a live token-usage indicator, enhanced session exploration features, and compatibility with multiple operating systems. Furthermore, its local API can be integrated into coding agents, facilitating automated reporting and real-time updates. With its focus on efficiency, ease of use, and robust tracking capabilities, Tokdash presents a valuable resource for developers looking to optimize their interactions with AI tools, ensuring they stay within usage limits while maximizing productivity.