dataset — independent software & tools
-
hyparquet
Parquet file parser for JavaScript
-
rag-ready-extractor
Convert webpages and PDFs into clean, structured data optimized for retrieval-augmented generation in a single API call.
-
openrouter-model-metrics
:trident: Hourly scraped provider throughput and latency data for every active model on OpenRouter.
-
doc2dataset
📄 Ingest documents into structured datasets for LLMs, ensuring numeric integrity and easy export across multiple frameworks with doc2dataset.