LangGraph
Low-level framework for building stateful, long-running AI agents with graph-based orchestration
LangGraph is LangChain's orchestration framework for building stateful AI agents. It organizes actions as nodes in a directed graph, enabling conditional branching, parallel execution, cycles, and persistent state. Agents can run for extended periods with durable execution that persists through failures. Features include human-in-the-loop inspection, short and long-term memory, and multi-agent coordination. Available in Python and TypeScript. The hosted LangGraph Platform offers managed deployments with a free developer tier.
Pricing: Free / monthly subscriptions
LangGraph Alternatives
Explore 40 products in the Frameworks & Stacks category. View all LangGraph alternatives.
Burr
Build stateful AI agents and applications as state machines, with a built-in tracing UI
Mastra
TypeScript-first AI framework for building agents, RAG pipelines, and workflows
Google ADK
Open-source agent development kit from Google for building multi-agent systems
Vercel AI SDK
Open-source TypeScript toolkit for building AI applications with streaming, tool calling, and agents
Pydantic AI
Type-safe Python agent framework with Pydantic validation, tool calling, and dependency injection
Semantic Kernel
Microsoft's SDK for building and orchestrating AI agents in .NET, Python, and Java
Also listed in
Work on LangGraph? Feature it at the top of Frameworks & Stacks.
Is your product missing?