openai

pypi package · declared by 263 of 2,343 sampled repositories · graph computed 2026-08-24

Counted from the runtime dependencies public repositories declare — not the resolved tree. A transitive dependency is a consequence; a declared one is a choice. Development dependencies are excluded because they repeat across every project in a language regardless of what is being built.

Declared with

ranked by association, not by count

Tools declared alongside this one, ranked by association strength
Declared with	Repositories	vs chance
anthropic	46 of 2,343	0.54
tiktoken	56 of 2,343	0.52
google-generativeai	14 of 2,343	0.47
python-dotenv	87 of 2,343	0.42
tenacity	36 of 2,343	0.42
dashscope	10 of 2,343	0.41
rouge-score	8 of 2,343	0.40
litellm	28 of 2,343	0.38
sentence-transformers	26 of 2,343	0.37
chromadb	16 of 2,343	0.37
nltk	18 of 2,343	0.37
pydantic	103 of 2,343	0.37
pymilvus	8 of 2,343	0.37
google-genai	19 of 2,343	0.37
reportlab	9 of 2,343	0.37
nest-asyncio	9 of 2,343	0.37
json-repair	12 of 2,343	0.36
ollama	12 of 2,343	0.36
datasets	31 of 2,343	0.36
posthog	8 of 2,343	0.35

Every pair above is counted from the same evidence: repo manifest.

Used instead

candidates · shares a neighbourhood and refuses to co-occur

No alternative measured. A pair qualifies only if it shares a neighbourhood and then fails to appear together against an expectation that it would — and almost everything that shares a neighbourhood does appear together. That is the test working, not a gap in the data: similarity alone would list this tool’s closest neighbours as alternatives, and most of them are things it is used with.