Research

EleutherAI's MIT-licensed unified benchmark suite — the de-facto standard for evaluating language models across 200+ tasks.

Fully open large language model from AllenAI: training code, weights, data, and eval all Apache-2.0.

MIT-licensed framework for evaluating LLMs and AI systems — build custom evals, run model comparisons, log results.

Autonomous AI research agent that searches the web and produces detailed, cited research reports in minutes.

Microsoft's graph-based RAG: build knowledge graphs from documents for global, multi-hop reasoning beyond vector search.

Stanford's LLM-powered knowledge curation agent that researches any topic and generates a full Wikipedia-style article.

Stanford CRFM's reproducible, multi-metric benchmark framework for evaluating any foundation model.

AI agent that retrieves, reads, and synthesises answers from scientific PDFs with citation-level accuracy.

Pythonic client for the arXiv API: search, download, and stream 2M+ preprints by query, author, or ID.