Skip to content

Third Eye

See where your AI coding money goes. Self-hosted dashboard for Claude Code, Cowork, and Codex CLI — all data stays on your disk.

Install

$git clone https://github.com/fien-atone/third-eye

Install command taken from the project's README or registry entry. Always review code before running it.

Third Eye

See where your AI coding money goes.

Self-hosted dashboard that reads your Claude Code, Claude Desktop / Cowork, and Codex CLI session files from disk and shows you — in plain charts — how much you actually spent, on what, and when. No signup. No cloud. Your data never leaves your machine.


Why?

If you use AI coding agents every day, you probably have no clue how much that actually costs you.

  • Which model burns the most tokens — Opus or Sonnet?
  • Which of your projects eats your AI budget?
  • Do you spend more on debugging or writing new code?
  • Is prompt caching actually saving you anything?
  • When do you work, really?

The provider billing dashboards don't answer these. Third Eye does, at per-call granularity, across every session you ever ran — including the ephemeral ones from Cowork.

What you get

  • Cost breakdowns by model, project, activity, git branch — any date range, any aggregation (day / week / month)
  • Per-project drill-down — click any project, get the full story: files you edit most, tools you invoke, subagents you spawn, skills you trigger, MCP servers you lean on
  • Projects registry — search, sort, rename, pin favourites; ⌘/Ctrl/middle-click any row to open the project in a new tab
  • Customizable widget dashboards — drag, resize, add and remove widgets on both the Dashboard and per-project view; every widget adapts to the size you give it (lists fit by row count, tables drop columns by priority, KPIs scale text via container queries, the heatmap sizes its cells exactly); layouts saved to your local DB and travel with the file across machines
  • Activity heatmap — 7×24 grid showing when you actually work on each project
  • Claude Code version tracking — see which CLI versions touched each project, distribution by cost / calls / tokens
  • Shareable project URLs — stable UUID in the hash, bookmark it, send it
  • Everything is local — SQLite file on your disk, you control it and can share it as-is
  • 5 languages · Light / Dark / System theme · timezone-aware · mobile-friendly

Quick start

Docker (recommended)

git clone https://github.com/fien-atone/third-eye
cd third-eye
docker compose up -d --build

Open http://localhost:4317. The container mounts your ~/.claude and ~/.codex read-only, re-ingests every 15 minutes, and survives reboots.

Node (no Docker)

git clone https://github.com/fien-atone/third-eye
cd third-eye
npm install
npm start

Open http://localhost:4317. To auto-refresh, open the gear icon in the header and enable Settings → Auto-refresh (off by default; pick an interval from 1m to 1h).

For headless / Docker setups without UI access, see DOCS.md for the legacy THIRD_EYE_INGEST_INTERVAL_MIN env var and npm run schedule:install cron-based path.

Let an AI do it for you

If you'd rather just tell your AI assistant, paste this prompt into Claude Code, Cursor, ChatGPT, or any other coding AI:

Similar plugs

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro,…

Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Devin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini…