Open-source tools track what AI coding agents really spend in tokens and cost
_jaydeepkarale · x · 2026-09-20
Two tools for monitoring AI coding agent consumption:
- Token Monitor (javis-ai): a local-first desktop widget tracking token usage, costs, and limits across 37+ AI coding tools.
- Splunk Token Meter: an open-source tool showing what coding agents actually consume during development—tokens, cost, tool calls, latency, and agent activity—instead of just "task completed." Supports Claude Code, Codex, Cursor, OpenCode, Kiro, and Pi.
The core point: as agents become more autonomous and make dozens of model/tool calls per task, "how much did it cost to get there" matters as much as "did it finish."
More from coding & agent
- Jev ecosystem explodes overnight: browser-use's jev-ultrafast hits ~8k stars, books flights in 7.1s — udmrzn · 2026-09-20
- Dev's custom reality-check skill returns a clean bill of health for beads_viewer — doodlestein · 2026-09-20
- TurnPanel launches public beta: a local-first AI workspace that operates your computer — Scobleizer · 2026-09-20
- Sutro Open-Sources jev-align, a CLI That Aligns Jev AI Functions With Your Judgment via GEPA — RichmanRonald · 2026-09-20
- Two vLLM bugs hid in plain sight: Mamba state cache, decode-before-prefill and a 32-bit wrap — AI Engineer · 2026-09-20
- Browser Use CEO: "browsers are dead" — CLI agents beat browser UIs 10x — annetgriffin · 2026-09-20