Laminar
Open-source all-in-one platform for engineering AI products
Start new thread

Laminar - Open-source all-in-one platform for engineering AI products

by•
Laminar is an open-source platform where you can trace your LLM app, run evaluations, label production data and use it to improve your prompts. Laminar is fast, reliable and offers best-in-class DX. It’s written in Rust and built on top of a modern tech stack.

Add a comment

Replies

Best
Incredible product and team!
Maker
thank you Sumanyu!
Congrats on the launch guys! I love to see the progress - it looks so easy to setup now 👀
This looks very exciting! I've just sent this to our engineering team to use.
Maker
Awesome, thank you Ivan!
Product that all of us need! Great job!
Maker
thank you!
Great job team! Really congrats
Huge congrats to the Laminar team on today's launch! I love how you're streamlining AI product engineering into one open-source platform. Quick question: How do you envision developers leveraging Laminar to improve their LLM app prompts - are there any specific use cases or success metrics you're excited to see emerge from the community?
Maker
thanks! There are two things we are looking forward to – human-aligned llm-as-a-judge and dynamic few shot examples. First is that LLM-as-a-judge is of no use, and may even be harmful, unless it is aligned to quality human labels. Second is that few shot examples work much better if they are relevant to the current input. And you can use Laminar for both!
Congrats! I've been looking for tools to manage data labeling and evaluations. Cool product!
Have over 45k pipeline runs with Laminar -- love these guys
Although I am not building on AI as of now, Laminar is the only viable way that I envision for myself when I will finally do! Amazing product and even more amazing team, congrats on the launch! Alga!!
Hey I’m genuinely impressed by how you’re helping developers trace and improve LLM applications. The way you approached the challenge of making this process so accessible and effective really stands out. We’re working on something for founders that could really benefit from insights like yours. Sent you both an email () with a bit more context if you’re open to it. Cheers, Johannes
First
Previous
12