LangGraphJS is a TypeScript framework for building stateful, long-running agents using a graph-oriented orchestration model. It focuses on durability, memory, and human-in-the-loop capabilities for complex tasks.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
LangGraph — used by Replit, Uber, LinkedIn, GitLab and more — is a low-level orchestration framework for building controllable agents. It enables agent orchestration with customizable architectures, long-term memory, and human-in-the-loop to reliably handle complex tasks. The repository provides the LangGraph library and related ecosystem components for JavaScript/TypeScript environments.
How it works
LangGraph provides durable execution, human-in-the-loop capabilities, comprehensive memory, and debugging/observability hooks through LangSmith. It is designed to support long-running, stateful workflows and agents, offering a low-level foundation to orchestrate agent behavior rather than higher-level agent designs.
Getting started
npm install @langchain/langgraph @langchain/core
This indicates the installation commands users should run to integrate LangGraph with core LangChain components.
Recent releases
- @langchain/langgraph@1.4.9 (2026-08-03): Patch Changes
- @langchain/langgraph-ui@1.4.4 (2026-08-03): Patch Changes
- @langchain/langgraph-cli@1.4.4 (2026-08-03): Patch Changes
- @langchain/langgraph-api@1.4.4 (2026-08-03): Patch Changes
- @langchain/vue@1.0.29 (2026-07-21): Patch Changes
Traction
3175 stars, 539 forks, 95 open issues (as reported in the repository metadata).
Behind the repo
LangGraph is developed by LangChain Inc and integrates with LangChain ecosystem components; it is used in multiple large-scale companies including Uber and LinkedIn. The repo provides language/technology details and links to related projects in the LangGraph ecosystem.
Caveats
License: MIT. Created 2024-01-09. Last push 2026-08-04. Main language: TypeScript. Open issues: 95. License and age are the factual cautions with regard to governance and maintenance expectations.