token usage

unbox-ai is an open-source CLI and local viewer for inspecting AI agent traces. It visualizes token usage, latency, tool calls, and repeated context in a bundle-analyzer-style interface, and also includes read-only commands for agents and a live AI SDK DevTools mode.

A Claude Code status line that shows session size, next-turn cost, and remaining budget before you type.

A web calculator that estimates the electricity use and carbon emissions of AI token usage, with everyday comparisons, example workloads, and a detailed methodology page.

Conan is a native macOS app that adds a live HUD around Claude Code, showing prompts, tool calls, skills, context usage, and session activity in real time. It’s a paid one-time purchase for Apple silicon Macs.

A field study on AI coding agents showing that a large share of token spend comes from re-reading files, with data from 47 sessions and discussion of memory-layer fixes.

A local-first, privacy-preserving usage meter for AI coding tools. It reads local transcripts to estimate token usage, cost, focus time, and achievements across tools like Claude Code, Codex, Kimi, and Qwen CLI.

A blog post describing an evaluation harness for comparing agentic coding tools and prompts across realistic SWE tasks, with token-cost results and model-specific behavior notes.