We’re building the future of agents
LangChain provides the agent engineering platform and open source frameworks developers need to ship great agents faster.
Our mission
We believe that LLMs are extremely powerful. They are more powerful when put to work through agents that can use data and take actions. Even though generative AI is evolving at a rapid pace, agents are still hard to make reliably good. Our mission is to figure out what the future of agents look like, and create tools that make it easy to build them.
We develop open source projects to stay ahead of the best patterns for building agents. Then, we incorporate these learnings into LangSmith - our commercial agent engineering platform. LangSmith helps companies understand, improve, and ship agents as fast as possible, whether they use our open source frameworks or not.
The LangChain story
LangChain started as Harrison Chase's side project in late 2022. It was a single Python package pushed from a personal GitHub account with no grand plan behind it. Then ChatGPT launched, and everything changed.
Harrison teamed up with co-founder Ankush Gola to start LangChain, the company, in early 2023, and we've been building ahead of the industry ever since. After LangChain, we launched LangGraph to give developers control over complex agent systems, with a runtime built for production.
As we shipped more agents, we saw a gap in tooling for testing and debugging them. We launched LangSmith, an independent commercial platform, for AI observability. We quickly added services for agent evaluation, deployment, and a no-code agent builder. Most recently, we released an agent harness called Deep Agents for autonomous, long-horizon tasks.
Today, we work with 35% of the Fortune 500, have crossed 1 billion open source downloads, and ingest over 1 billion events per day on LangSmith. We're headquartered in San Francisco, with offices in New York, Boston, and Amsterdam.
Our operating principles
Build something great
We're here to build something great. We aim high. We don’t settle for okay and don't accept mediocrity. Seeing something not done well drives us to dive in and raise the bar together. We ship v0s earlier than is comfortable because greatness is paved with rapid iterations and real-world feedback. We sweat the details of our craft to build things that make a difference.
Embrace hot takes
Hot takes help us challenge the status quo and draw attention to a problem or a kernel of truth without forcing us to think through every last detail. They allow for more creative ideas and can make feedback less personal. Hot takes encourage opinions from all levels of the organization, surfacing up issues we can learn from more quickly, and prompt us to update priors.
Maximum agency
We are a team of owners, not renters. We are each the benevolent dictators of our domains. We drive ideas forward with conviction, and listen with humility. We bias toward action and show rather than tell. Execution is more important than just having ideas. Whether we work solo or lead a group, we are responsible for the ultimate result. We don’t wait for permission to make things better.
Run to the roar
We run toward problems because we care about making the company and our customers successful. We operate in a very fast moving space, and we lean into that intensity rather than shrink from it. We dive in to fight the fire. We solve problems head-on with grit and resilience and trust our teammates do the same. We stay relentless and work hard sustainably to build something great together.
We’re hiring across all teams
LangChain has big ambitions. We’re hiring across the board. Explore open roles on our careers page, and make a mark on how the world uses AI.
Ready to start shipping reliable agents faster?
LangSmith, our agent engineering platform, helps developers debug every agent decision, eval changes, and deploy in one click.