Harbor x LangChain: A Unified Stack for Evaluating Agents
Harbor integrates with LangChain agents to create a unified stack for evaluating them, using a langgraph.json registry and make_graph factory to run agents in isolated sandboxes. It supports cloud sandboxes for horizontal scaling and reproducible environments, with the ability to switch providers without affecting the agent, dataset, or verifier. The system unifies LangSmith sandboxes and observability, enabling detailed tracking of agent decisions and evaluations.
More from Langchain
Why managed agents are the next big thing in agent building
Managed Deep Agents gives developers a managed way to build, run, and deploy Deep Agents with built-in runtime, streaming, sandboxes, evals, memory, and auth.
langchain.com··Mads Kristian Nylund·AI InfrastructureAI-agents
LangSmith BYOC on AWS is generally available
LangSmith Bring Your Own Cloud is now generally available on AWS, giving Enterprise teams managed observability, evaluation, and deployment inside their own VPC.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI Platforms
What is an AI agent?
Learn what AI agents are, how they work in an LLM loop, and where workflows fit so you can build reliable, production-ready autonomous systems.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI-agents