We built any-llm because we needed a lightweight router for LLM providers with minimal overhead. Switching between models is just a string change : update "openai/gpt-4" to "anthropic/claude-3" and you're done.
It uses official provider SDKs when available, which helps since providers handle their own compatibility updates. No proxy or gateway service needed either, so getting started is pretty straightforward - just pip install and import.
Currently supports 20+ providers including OpenAI, Anthropic, Google, Mistral, and AWS Bedrock. Would love to hear what you think!
Comments URL: https://news.ycombinator.com/item?id=44650567
Points: 56
# Comments: 43
Login to add comment
Other posts in this group
Article URL: https://orgmode.org/worg/org-tutorials/index.html
Article URL: https://www.bsc.es/news/bsc-news/countries-ac
Article URL: https://github.com/scottvr/wtffmpeg
Comments URL: https://news.ycombin
I try and keep subscriptions down to a minimum, although there are several that I think are essential to my workflow. I'm interest to know what everyone's essential subscriptions are.
Mine are E
