#llm-cost

A Claude Code plugin that shows exactly where your AI coding session wasted tokens — and how to fix it. Flags waste, never quality. Runs locally.

AI Runtime Meter gives developers a live token, cache & cost meter for Claude Code. Shows tokens, cache, model, source , cost and session totals per request. Run from any terminal or IDE.

Find out what your Claude Code sessions cost, and how much of the bill is re-reading what the agent already read.

OpenAI-compatible LLM proxy that races multiple providers in parallel and returns the fastest usable answer. Cut token cost, slash latency, handle flaky free/local model tiers. Bring your own keys, no markup. Zero-dependency install on macOS & Linux (Apple Silicon, ARM64 SBCs).

Beautiful zero-dependency dashboard for Claude Code usage — equivalent API cost, token breakdown, 5h-window usage gauge, per-model/project trends. Reads ~/.claude/projects, renders offline HTML.

What each coding-agent task cost, read off Claude Code's own transcripts — per session, branch or day. No API key, nothing leaves the machine.

Measure Claude Code token use, cut the waste, and prove your savings with a real before and after. Local, private, measured from your own usage counters.

Measure what your AI coding sessions actually cost, then act on advice derived from your own numbers — not someone else's.