Quick answer
Run whoburnedmore with the CLI command npx whoburnedmore. Existing commands and links remain supported.
Search intent
The reader is evaluating open-source options for AI coding usage tracking.
Best for
Developers and teams who want transparent usage measurement.
Check the data boundary
The tracker should make it obvious whether it uploads raw logs, source code, prompts, or only aggregate usage.
- Read code.
- Inspect network calls.
- Check docs.
Compare coverage honestly
Some tools only track Claude Code. Others track multiple coding agents. Choose based on the tools your team actually uses.
- Claude Code
- Codex
- Gemini CLI
- Cursor
- Copilot
Look for useful output
A tracker should answer practical questions: what burned most, when, in which tool, and whether cost is rising.
- Daily totals
- Model mix
- Project view
- Export
Decide whether you need social features
A CLI-only tracker may be enough for private diagnostics. A leaderboard adds motivation and team visibility when used carefully.
- Private report
- Team board
- Public profile
Short answer for open source ai usage tracker
The practical answer is to measure the workflow before changing tools or plans. Choose an open source AI usage tracker that reads logs locally, avoids source code upload, supports your tools, shows useful cost breakdowns, and has a clear public/private mode. Then review the result against the intended outcome: whether the work shipped, whether the agent got stuck in a loop, and whether the same task should use a smaller prompt, a cheaper model, or a different AI coding product next time.
This is also why the page links to authoritative external sources and to related whoburnedmore guides. Pricing pages explain the vendor unit; your local usage history explains what that unit means in practice. Keep both views together before making a budget, upgrade, or team-policy decision.
Mistakes to avoid
Optimizing before measuring
It is tempting to change plans, switch tools, or clamp down on usage as soon as open source ai usage tracker becomes a concern. That usually hides the real issue. Measure the current workflow first, then decide whether the problem is volume, scope, model choice, team policy, or one unusually expensive session.
Comparing vendor units directly
A request, credit, ACU, message, token, and quota are not interchangeable units. Convert each tool back to the work it produced: the feature, bug fix, review, prototype, or incident response. That makes cross-tool comparison fair enough to act on.
Treating high burn as automatically bad
A high-burn session can be waste, but it can also be the session that unblocked a release. Add outcome notes before judging the number. The goal is not low usage; the goal is useful, explainable usage that the team can repeat.
Practical playbook
What to measure first
Start with the signal most likely to change behavior for this topic: local parsing. For someone searching open source ai usage tracker, the useful answer is not a generic definition. It is a repeatable way to decide whether the current workflow is healthy, whether the cost is justified, and which next action will reduce waste without killing useful AI experimentation.
How to turn it into a habit
Use a simple weekly rhythm: measure the biggest burn, label the task, record whether it shipped value, and change one prompt or routing rule. The sections above cover check the data boundary, compare coverage honestly, look for useful output, and decide whether you need social features. Those are the pieces that make the guide actionable instead of another pricing summary.
How whoburnedmore fits
whoburnedmore is the measurement layer, not the policy layer. It reads local AI coding-agent usage, keeps source code out of the upload path, and gives you a shared burn view. That means this guide can stay focused on decisions: when to upgrade, when to narrow context, when to switch tools, and when a high-burn session was actually worth it.
Decision checklist
Can you explain why open source ai usage tracker matters for a real task this week?
Do you know which tool, model, project, or workflow created the largest burn?
Is the next action a smaller prompt, a different tool, a plan change, or a team policy update?
Can you review the result without uploading source code or raw prompt content?