Open source toolkit to analyze your ChatGPT/Claude usage from exports
A new open-source toolkit has been released for analyzing personal LLM usage from ChatGPT and Claude exports. The toolkit provides various analytics including model adoption timelines, prompt engineering effectiveness, and cost efficiency metrics. Users can run the toolkit locally, ensuring their data remains private and secure.
- ▪The toolkit allows users to analyze their LLM usage without sending data off their machines.
- ▪It includes features like model adoption timelines and prompt technique tracking.
- ▪Users can compute cost efficiency metrics and generate formatted reports.
Opening excerpt (first ~120 words) tap to expand
LLM Export Analytics Privacy-first tools for analyzing your personal LLM usage from official ChatGPT and Claude exports. Everything runs locally. Nothing leaves your machine. Turn your raw export data into: model adoption timelines, topic breakdowns, prompt engineering effectiveness metrics, cost efficiency analysis, and formatted reports. Try it now git clone https://github.com/noah-chelednik/llm-export-analytics.git cd llm-export-analytics ./run_pipeline.sh --sample This runs the full pipeline against included sample data so you can see what it produces before using your own exports.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.