langgraphjs
Framework to build resilient language agents as graphs.
What is langgraphjs?
Framework to build resilient language agents as graphs.
Overview of langgraphjs
What it is
LangGraph is a low-level orchestration framework for building stateful language agents as graphs. It is developed by LangChain Inc and is used by companies such as Replit, Uber, LinkedIn, and GitLab. The library enables agent orchestration with customizable architectures, long-term memory, and human-in-the-loop capabilities to handle complex tasks.
Key features
- Durable execution: agents persist through failures and automatically resume from where they left off.
- Human-in-the-loop: inspect and modify agent state at any point during execution.
- Comprehensive memory: short-term working memory for ongoing reasoning and long-term persistent memory across sessions.
- Debugging with LangSmith: visualization tools that trace execution paths, capture state transitions, and provide runtime metrics.
- Production-ready deployment: scalable infrastructure for stateful, long-running workflows.
Use cases
LangGraph is suitable for building any long-running, stateful workflow or agent. It can be used standalone or integrated with LangChain products. The repository mentions that it is used by Replit, Uber, LinkedIn, and GitLab for building controllable agents.
Getting started
bashnpm install @langchain/langgraph @langchain/core
License and pricing
The license is MIT. The project is open source.
Based on the project's public README and repository metadata.