PY

pyllms

Evaluation·infrastructure·open·#825 of 886·+99·Rising

57.1

Low

High confidence

Minimal Python library to connect to LLMs (OpenAI, Anthropic, Google, Groq, Reka, Together, AI21, Cohere, Aleph Alpha, HuggingfaceHub), with a built-in model performance benchmark.

Pillar Breakdown

Adoption

35%

53.8

Maintenance

30%

63.1

Friction

20%

88.4

Ecosystem

15%

29.5

Momentum

0.65Rising
7d change -0.40
High confidence

In Evaluation

Ranked #51 of 57

Similar Tools