Why I started logging every LLM call through a local proxy
Most teams have no idea how many tokens they burn or which prompts actually work. Running your own proxy fixes that.
Read the note 1 min read
From the notebook
4 notes on this topic.
Most teams have no idea how many tokens they burn or which prompts actually work. Running your own proxy fixes that.
A French dev got sick of Prometheus configs and wrote a monitoring tool that fits in one binary, one YAML file, and one SQLite database.
The National Institute of Standards and Technology maintains atomic clocks in Colorado and Maryland, then serves that time over the internet. The API is simpler than you think.
A new LLM observability tool runs without PostgreSQL or Redis. That is not a feature list, that is an architecture decision.