# LangGraph

> Open-source, low-level orchestration framework and runtime for building stateful, controllable agents

Source: https://dontaskagain.com/langgraph
Website: https://www.langchain.com/langgraph?utm_source=dontaskagain
Pricing: Freemium
Categories: [Agent frameworks](https://dontaskagain.com/categories/agent-frameworks.md), [Open source](https://dontaskagain.com/categories/open-source.md)
Listed: 2026-10-19
Updated: 2026-10-19

LangGraph is an open-source agent runtime and low-level orchestration framework from LangChain. It lets developers' agents handle complex, long-running tasks reliably by giving precise control over how an agent reasons, calls tools and moves between steps, while still letting it act on its own.

**Key features:**

- Design single-agent, multi-agent and hierarchical control flows with low-level graph primitives.
- Add human-in-the-loop checks to moderate, steer and approve agent actions.
- Persist memory so conversation history and state carry across sessions.
- Stream tokens and intermediate steps to show agent reasoning in real time.
- Use any model provider, with high-level abstractions or fine-grained control.
- Debug and deploy agents through LangSmith Studio and LangSmith Deployment.

LangGraph is available for Python and JavaScript under the MIT license and can run on any infrastructure. Hosted deployment goes through LangSmith, whose free Developer plan has no deployments and whose Plus plan ($39 per seat a month, then pay as you go) includes one free serverless deployment.

## More agent frameworks

- [Browser Use](https://dontaskagain.com/browser-use.md): Open-source browser agent and cloud browsers that complete web tasks like form filling, checkout and data extraction
- [Stagehand](https://dontaskagain.com/stagehand.md): Open-source SDK for building browser agents with Playwright-style APIs plus natural-language act, observe and extract
- [CrewAI](https://dontaskagain.com/crewai.md): Multi-agent framework and enterprise platform for building, running and governing teams of role-based agents
- [OpenAI Agents SDK](https://dontaskagain.com/openai-agents-sdk.md): OpenAI's lightweight Python framework for building agents with tools, handoffs, guardrails, sessions and tracing
- [Mastra](https://dontaskagain.com/mastra.md): Open-source TypeScript framework for building agents and workflows with memory, evals and observability
- [Pydantic AI](https://dontaskagain.com/pydantic-ai.md): Type-safe Python agent framework from the Pydantic team with model-agnostic agents, tools and evals
- [Agno](https://dontaskagain.com/agno.md): Open-source agent framework and self-hosted runtime for building agents, teams and workflows in your own cloud
- [LlamaIndex](https://dontaskagain.com/llamaindex.md): Document parsing and extraction platform (LlamaParse) plus the open-source LlamaIndex framework for document agents
- [AI SDK](https://dontaskagain.com/ai-sdk.md): Open-source TypeScript toolkit from Vercel for building AI apps and agents with streaming and multi-model support
- [Letta](https://dontaskagain.com/letta.md): Research lab behind MemGPT building stateful agents with persistent, self-improving memory