langchain-ai/langgraphjs

Health v2 · maintenance only

Adoption not part of the score

3236 stars · 563 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

LangGraph.js is a TypeScript/JavaScript framework for building stateful, long-running LLM agents as graphs of nodes and edges, mixing deterministic code with LLM-driven steps. It provides durable execution, streaming, human-in-the-loop interrupts, and a runtime for orchestrating complex agent workflows.

Use cases

• build a multi-step LLM agent in TypeScript
• orchestrate AI agents as stateful graphs
• add human-in-the-loop approval to agent workflows
• build long-running stateful agents with durable execution
• mix deterministic code with LLM tool-calling steps
• stream agent state updates to a UI
• build a calculator or tool-calling agent with Claude or OpenAI

When to choose

• you need fine-grained control over agent control flow in JavaScript/TypeScript
• you need stateful, long-running agents with persistence and interrupts
• you want to combine hand-coded steps with LLM-driven steps in one workflow
• you're already in the LangChain ecosystem and need low-level orchestration

When to avoid

• you want a simple prebuilt agent loop with minimal boilerplate - use higher-level LangChain agents
• you're building in Python and prefer the original LangGraph
• your app doesn't involve LLMs or agentic workflows
• you need a no-code agent builder

Facets

framework · maturity active

agent-framework workflow-automation llm-inference state-management streaming large-language-models artificial-intelligence developer-tools cross-platform langgraph langchain llm-agents graph-api human-in-the-loop durable-execution orchestration ai-agents nodejs typescript

Member repositories

For agents

markdown · JSON · MCP: product_card(name="langchain-ai/langgraphjs")