Tokdash is a locally-run dashboard that tracks token usage and costs for AI coding assistants, filling a gap left by tools that automatically delete session history after ~30 days. It offers token breakdowns, historical usage calendars, subscription quota tracking, and performs significantly faster than comparable tools, making it useful for developers who want persistent, detailed visibility into their AI tool consumption.
Summaries like this, in your inbox every morning.
Sign up free →What happened
Tokdash is a local dashboard that tracks token usage and costs across AI coding tools like Claude Code and Gemini CLI. It offers exact token counts (input/output/cache breakdowns), a contribution calendar with usage metrics, per-session drill-down, and quota tracking with reset countdowns for services like Codex and Claude.
Why it matters
AI coding tools delete local session history after ~30 days by default, which can silently shrink your usage record unless you configure retention manually. Tokdash preserves that history locally and provides visibility into spending and quotas, helping developers monitor their AI tool costs and usage patterns without relying on cloud-hosted logs.
What to watch
The tool runs as a local background service (http://127.0.0.1:55423 by default) and is available now via Python installation; it is roughly 30× faster than earlier cold scans and 15× faster than comparable tools like ccusage in the same local benchmark. Remote access is supported via SSH forwarding or Tailscale Serve, and integrations with statusline indicators in coding agents are available in the docs.
No discussion yet for this article
Get curated AI news from 200+ sources delivered daily to your inbox. Free to use.
Get Started FreeFree · takes 30 seconds · unsubscribe anytime
1 minute a day. The AI essentials.
200+ sources · Email / LINE / Slack
