saive-client added to PyPI

A new Python library called saive-client has been released on PyPI. It automatically tracks token usage for OpenAI, Anthropic, and Google's generative AI models. The tool operates in the background without accessing prompt or response content.
Key takeaways
- Tracks token usage for major LLM providers
- Operates asynchronously in the background
- Does not access sensitive prompt or completion data
- Aims for zero-friction LLM footprint reporting
Why it matters
Developers and businesses can now monitor their AI costs more effectively without complex integrations. This allows for better budget management and optimization of AI tool usage, ensuring predictable expenses for generative AI applications.



