Show HN: Mirascope – The LLM Anti-Framework
github.comHi! I'm William Bakst, one of the co-authors of Mirascope. We're really excited about what we've built in this v2 release. Any and all feedback is welcome with open arms :)
Some useful links:
- [LLM Docs](https://mirascope.com/docs/learn/llm)
- [Why Mirascope](https://mirascope.com/docs/why)
- [Mirascope Quickstart](https://mirascope.com/docs/quickstart)
This has been one of my favorite frameworks to use for AI development. I feel like it is pretty dead-simple to use. But also has a great quality: it gets the f** out of your way when you need it to. I feel like with a fast moving layer beneath it (ie ai providers), I need to be able to adopt and experiment with new features from the providers, without having to wait for your library to update.
I think the api generally is great taste. Having typed functions as the core abstraction (which shares some similarity with Dspy Signatures) was a great move.
Congrats on the launch, can't wait to see the platform come together more and more.
This means a lot! I'm glad our philosophy in how we've decided to engineer Mirascope has come through so clearly!
We have so much in the works
I love how it does not lock you into an agent loop. Everything's composable and you use as much or little as you need. Can't wait for the Typescript version!
TypeScript coming so soon
high taste. finally someone that let's me take care of the loop myself, no magic...
the only magic is how magical it feels to be in control
neat! Looks interesting
we're aiming for the neatest :)
looks great!
Thank you!!