CodeBurn

Hey PH, I'm Resham, the person behind CodeBurn.

AI coding tools don't tell you where your money goes. The bill shows a total, and that's it. Which model? Which project? Was it work that shipped, or an agent re-reading the same file over and over?

The thing is, the answer already exists. Every AI coding tool Claude Code, Cursor, Codex, Copilot, and 36 more writes detailed session logs to your own disk. Nobody was reading them.

CodeBurn reads them. Here's everything it does:

📊 Understand your spend
• Every token and dollar broken down by task, model, project and by pull request, so you see which PRs your budget actually shipped
• A spend punchcard: which hours and weekdays you burn the most
• Session browser with titles, so you find work by what it was about
• Workflow insights: how often you correct the AI, how long until it makes its first edit, which files it keeps reworking

🔥 Cut your spend
• Optimize finds the waste: cache bloat, retry tax, expensive models doing work a cheaper one handles fine
• It applies the fix for you and tracks what the fix actually saved. Undo included
• Compare any two models on your own real usage: cost per edit, one-shot rate
• Budgets with warnings, subscription plan and overage tracking, live quota windows

🖥️ Wherever you work
• CLI: one command, full dashboard in your terminal
• Desktop app for Mac, Windows and Linux nothing else to install, the engine is bundled
• macOS menu bar: today's burn always visible, with forecasts and quota pace
• Web dashboard served from your own machine
• GNOME panel extension for Linux
• All of them read the same local data, so they always agree

🔒 Built on two rules
• Honest: when a cost is estimated instead of exact, it says so
• Yours: open source, MIT license, no account, nothing ever leaves your machine. Genuinely free

There's also an MCP server, so your AI agent can check its own spending. Yes, really.

🎁 For PH folks: nothing to unlock it's already free. If your AI tool isn't supported yet, open an issue and I'll personally prioritize it.

I'll be in the comments all day. Ask me anything. 👇

→ codeburn.app

I came to CodeBurn from a somewhat unusual direction.

I spent years in strategy and venture investing looking at companies deploying AI, and later moved into an operating role partly because I wanted to understand the problem from inside an enterprise.

Then I started building with coding agents all day myself, and one thing became very obvious: provider dashboards are good at telling us what we consumed. They are much worse at telling us what the consumption actually accomplished.

Resham had already been attacking that problem with CodeBurn. What immediately interested me was how much ground-truth information was sitting locally in agent sessions and git history.
Which project used the money? What was the agent actually doing?How many times did it retry?What did it reread?Did any of that work become a commit or PR?That is the layer we're building out.

The longer-term question we're particularly interested in is cost per useful unit of AI work, rather than cost per token.

For this launch, I’d especially love feedback from people who use multiple coding agents heavily:

What do you still feel blind to? What metric would actually make you change how you use your agents?

I’ll be around here all day. Looking forward to your inputs.

the attribution thread in here is the most honest writeup of this problem I've seen, the "unattributed rather than smearing it somewhere plausible" choice especially. curious how this handles fan-out though. I run a lot of orchestration now where one task spins up 5-10 subagents in parallel, each burns its own tokens on its own slice, and only one final step merges their output into a PR. none of those side agents individually "did" the PR, the value only exists at the synthesis step. does codeburn have any concept of a parent task grouping child sessions, or does that show up as several expensive unattributed sessions and one cheap one that happens to touch the PR?