#66th of 9 in Agent frameworks and SDKs
langgraph
Python framework for building long-running, stateful agents as graphs
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 43.2k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
26,997 on 24 Mar 202643,233 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
LangChain is hiring: 100 open roles
Overview
LangGraph is a low-level Python library for orchestrating stateful agents and workflows as graphs, inspired by Pregel and Apache Beam. It provides durable execution that resumes after failures, human-in-the-loop interrupts to inspect and edit state, and short-term and long-term memory. It can be used without LangChain; tracing and managed deployment go through the separate LangSmith products.
Who it is for: Python developers building custom stateful agents and workflows
Strengths
- Durable execution resumes agents from where they stopped after a failure
- Interrupts allow inspecting and modifying agent state mid-run
- Built-in short-term and long-term memory across sessions
- Usable without LangChain; a JS/TS port (LangGraph.js) also exists
Weaknesses
- Low-level API; higher-level agent building is pushed to the separate Deep Agents package
- Tracing UI and managed deployment rely on LangSmith, a commercial LangChain product
- No visual builder in this repo; agents are defined in code only
- README gives no RAM, storage or persistence backend requirements
What it needs
- no GPU
- Models: model-agnostic; LangChain integrations optional
Also in Agent frameworks and SDKs
See all 9| Rank | Project | Score |
|---|---|---|
| 1 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| 2 | browser-usePython library that lets an LLM agent control a web browser | 87 out of 100 |
| 3 | crewaiPython framework for multi-agent workflows with role-based Crews and event-driven Flows | 77 out of 100 |
| #4 | agnoPython SDK and runtime for building and serving agents behind a REST API | 69 out of 100 |
| #5 | llama_indexPython framework for RAG and agent apps over your own data | 68 out of 100 |