PeekAI tracks Python AI agent token use and cost locally
PeekAI is an tool for debugging Python and checking their costs. It automatically tracks OpenAI and Anthropic calls, then shows the steps of a run in a waterfall-style view. Token use and cost can be checked for each step, so expensive parts are easier to find.
are also tracked. Past runs can be replayed, and the model can be swapped to compare cost and quality on the same run. It does not need a cloud service or account, and it stores data locally in SQLite.
Setup is `pip install peekai`, then calling `peekai.init()` in the code. It is an early 0.1 release under the .
Key points
- It tracks OpenAI and Anthropic calls in Python .
- It shows each run step by step and reports token use and cost per step.
- It can replay past runs and swap models to compare cost and quality.
- It works without a cloud account and stores data locally in SQLite.
- It is an early 0.1 release with an .