Name: LangSmith
Rating: 4.89 (18 reviews)

LangSmith is a platform to help developers close the gap between prototype and production. It’s designed for building and iterating on products that can harness the power–and wrangle the complexity–of LLMs.

LangSmith is a solution for developing, tracing, debugging, testing, deploying, and monitoring LLM applications. Integrates seamlessly with LangChain, but exposes SDKs for use outside of the LangChain ecosystem as well.

Been using LangSmith for a while now, and I've got to say, it's a game-changer for anyone developing with LLMs. The traces feature has been particularly invaluable for us, making debugging and understanding our AI Agent's actions much easier. Without it, we'd be lost in the complexity of LLM applications. LangSmith's comprehensive approach to the LLM development lifecycle, from development and collaboration to testing, deploying, and monitoring, is impressive. The platform's ability to provide full visibility into the sequence of calls has streamlined the way we debug and optimize performance. A must-have for teams working on LLM-powered apps!

Hi Product Hunt Community! I’m Harrison Chase, Co-Founder & CEO at LangChain. LangChain exists to make it as easy as possible to develop LLM-powered applications. We started with an open-source Python package when the main blocker for building LLM-powered applications was getting a simple prototype working. We remember seeing Nat Friedman tweet in late 2022 that there was “not enough tinkering happening" (https://twitter.com/natfriedman/...). The LangChain open-source packages are aimed at addressing this and we see lots of tinkering happening now — today, LangChain’s flexible abstractions power over 50K apps. The blocker is different today. While it’s easy to build a prototype of an application in ~5 lines of LangChain code, it’s still deceptively hard to take an application from prototype to production. The main issue that we see today is application performance — something that works ~30% of the time is good enough for a Twitter demo, but not nearly good enough for production. We’ve built LangSmith to solve this problem. Today, I’m excited to announce the general availability of LangSmith — our solution for LLM application development, monitoring, and testing. We initially launched LangSmith in closed beta in July 2023. Since then, we’ve received invaluable feedback from our early users and customers, and made significant improvements to the platform. We’ve also made heavy investments in our infrastructure to ensure that the platform is able to seamlessly scale to accommodate our rapidly growing user base. LangSmith is now trusted by companies like Rakuten, Elastic, Moody’s, Retool, and more. I also want to extend my heartfelt thanks to all our users for their support in shaping LangSmith into the platform it is today. Since launching, we’ve seen - Over 80K signups - Over 5K monthly active teams - Over 40 million traces logged in January alone We learned from our users more about the pain points that are common to building with LLMs, and we’re trying to solve those whether you’re building with LangChain or not. If you want to see LangSmith for yourself, sign up today: https://smith.langchain.com. We’ve removed the waitlist, so you can get building immediately. I hope you love it. My co-founder, Ankush Gola, is hosting a webinar today at 12pm PT if you’d like to learn more about LangSmith. You can sign up to tune in here: https://www.crowdcast.io/c/langs.... Feel free to post any feedback or questions here!

The big day is here — LangSmith is now open to all!

We started building Ting without LangSmith and we were flying blind. Diagnosing issues downstream felt like guesswork. Since bringing LangSmith in, we’ve been able to trace problems through the entire prompt path and actually understand what’s going on. We’re still evolving how we use it, but even early on it’s helped us move faster and get closer to that “this feels good” moment.

We absolutely could not build this product with LangSmith for traces, datasets, annotation queues, and evals. We've become big power users! I use to build AI apps before nice tracing tools like this existed and it's like night and day having a tool like this. We considered Langfuse, but I already had experience with LangSmith so for speed purposes we went with LangSmith.

LangSmith’s real-time analytics and versioning keep our AI agents rock-solid -- so everything just works better.

LangSmith

Build and deploy LLM applications with confidence

Build and deploy LLM applications with confidence

LangSmith

Build and deploy LLM applications with confidence

Build and deploy LLM applications with confidence

Similar Products

LangSmith General Availability

LangSmith Launches

Do you use LangSmith?

LangSmith Launches

Do you use LangSmith?

You might also like