This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
ACM TRACKER
Time tracking that knows what your AI agents really cost
Self-hosted time + cost tracker. Local app, remote DB, single source of truth for what work reallOpen-source, self-hosted time + cost tracker where AI agents report their own work through MCP. Every task merges human time (hours × rate) with real AI spend (tokens × per-model price) on one timeline. See burn rate, margin per project, and cost per person — human + their AI. Connect Claude Code with 2 commands. Runs as a desktop app, single Docker image, PWA, or Helm chart. no per-seat pricing.
Hi Product Hunt 👋
I build software with AI agents every day, and at some point I realized I had no idea what a project actually cost me. My time tracker knew my hours — but nothing knew what Claude was burning in tokens on the same task.
So I built ACM-TRACKER around one idea: the agent reports its own work. It exposes an MCP server, and after each task your agent calls report_work with minutes, tokens in/out, and the model used. The server prices it against an editable per-model price table and logs it on the same timeline as human entries.
True task cost = Σ(human hours × rate) + Σ(tokens × model price). No estimates.
It also tracks margin: project rate (what you charge) vs member rate (what it costs you), live per project.
It's open source (AGPL-3.0), fully self-hosted, no per-seat pricing. You can run it as a desktop app (Win/macOS/Linux), a single Docker image with SQLite inside, a PWA, or a Helm chart on k8s.
If you bill clients while agents do part of the work, I'd love your feedback — especially on what you'd need to trust the cost numbers.
About ACM TRACKER on Product Hunt
“Time tracking that knows what your AI agents really cost”
ACM TRACKER was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #153 on the daily leaderboard. Self-hosted time + cost tracker. Local app, remote DB, single source of truth for what work reallOpen-source, self-hosted time + cost tracker where AI agents report their own work through MCP. Every task merges human time (hours × rate) with real AI spend (tokens × per-model price) on one timeline. See burn rate, margin per project, and cost per person — human + their AI. Connect Claude Code with 2 commands. Runs as a desktop app, single Docker image, PWA, or Helm chart. no per-seat pricing.
On the analytics side, ACM TRACKER competes within Time Tracking, Developer Tools, Artificial Intelligence, GitHub and Vercel Day — topics that collectively have 1M followers on Product Hunt. The dashboard above tracks how ACM TRACKER performed against the three products that launched closest to it on the same day.
Who hunted ACM TRACKER?
ACM TRACKER was hunted by Harrinson Gutierrez Coronado. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of ACM TRACKER including community comment highlights and product details, visit the product overview.
Harrinson Gutierrez Coronado