LangGraph
LangGraph is a low-level orchestration roof designed to create workflows with a long-lasting (stateful) agent holding status information. It offers basic infrastructure components such as durable execution, human-in-the-loop, and comprehensive memory management. Thanks to LangSmith integration, it allows monitoring and debugging execution paths.
LangGraph
100langchain-ai · AI Communities & Swarms
- You set up durable agent workflows that work for a long time and continue where they left off in error situations.
- During execution, you examine and modify the agent status to add human control to the workflow.
- You develop an agent with short-term working memory and status information with intersessional permanent memory
- • High number of open issues (514)
- ↑ PositiveHacker News
We chose LangGraph to build our coding agent
“One thing that's nice in LangGraph is the flexibility in what a node is. A node doesn't have to be an agent it can be any State manipulation function. So you can create nodes that exclusively do preprocessing or postprocessing and get your run loop as close as possible to just…”
- • NeutralHacker News
We chose LangGraph to build our coding agent
“I think the main thing LangGraph adds is a state machine framework for human in the loop with time travel. So if you have an authoring workflow where a doc goes through a bunch of steps, and at some steps the analyst might want to fix some LLM output manually, and try a couple…”
Verified against README · Oct 26, 2026 · source
My note
More in: AI Communities & Swarms
- MetaGPT★ 71,099 · 9 mo ago
- CrewAI★ 60,320 · yesterday
- Agno★ 42,987 · today
- ChatDev★ 34,628 · yesterday
- OpenAI Agents SDK★ 30,401 · today
- smolagents★ 30,151 · 2 days ago