#333 · Primary category: AI Agents & Automation
langgraphjs
Framework to build resilient language agents as graphs.
Project last updated:08/26/26
GitHub Stars
3.2K
Forks
565
Contributors
142
License
MIT
Why we included this project
For JavaScript and TypeScript teams, LangGraph is a low-level library for building agent workflows, and its practical value shows up when things go wrong. It models a run as a graph with shared state, so an agent that crashes mid-task resumes from its last checkpoint instead of starting over, and memory carries across sessions rather than resetting each time. Runs can also pause to wait for a human decision before continuing, which makes human-in-the-loop review practical. That combination of durable execution and explicit interrupts is what makes it workable for agents doing real work against external systems over long runs. It is not a ready-made assistant: you bring your own tools and LLM calls, and LangGraph provides the structure to shape multi-step reasoning into something predictable. If LangChain already supplies your components, LangGraph is the layer that decides how they flow together.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.