# langchain-ai/langgraph

Build resilient agents.

Repository: https://github.com/langchain-ai/langgraph
Canonical: https://ross.abutalabs.com/products/langgraph
Homepage: https://docs.langchain.com/oss/python/langgraph/
Language: Python
License: MIT
License Family: permissive
Topics: agents, ai, ai-agents, chatgpt, deepagents, enterprise, framework, gemini, generative-ai, langchain, langgraph, llm, multiagent, open-source, openai, pydantic, python, rag
Last push: 2026-08-26T20:57:44+00:00

## Health v2 (maintenance only)
Score: 91/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 80
- inputs: {"age_days": 1120, "days_push": 7, "days_rel": 14, "gap_med": 0, "n_releases_24m": 482}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 40503, forks 6830 (observed 2026-08-28T04:12:08.246001+00:00)

## What it is
LangGraph is a low-level orchestration framework and runtime for building, managing, and deploying long-running, stateful AI agents in Python. It lets developers mix deterministic hand-coded steps with LLM-driven agentic steps in a graph, with durable execution, human-in-the-loop interrupts, and short- and long-term memory.

## Use cases
- build a stateful multi-step LLM agent
- orchestrate multi-agent workflows with shared state
- add human approval checkpoints to agent runs
- build agents that survive failures and resume execution
- create a customer support chatbot with long-term memory
- mix deterministic business logic with LLM tool-calling steps
- build a RAG agent with controllable control flow

## When to choose
- you need fine-grained control over agent control flow and state
- you are building long-running, production-grade agents that need durability and memory
- you want human-in-the-loop oversight of agent execution
- you need multi-agent orchestration with shared, inspectable state

## When to avoid
- you just want a simple prebuilt agent loop with minimal setup - use LangChain agents or Deep Agents instead
- your application is a simple LLM call chain without state or branching
- you need a JavaScript/TypeScript-first codebase - use LangGraph.js instead

## Facets
- artifact type: framework
- maturity: stable
- function: agent-framework, workflow-automation, llm-inference, rag, chatbot, state-management
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python, cross-platform
- tags: llm-agents, graph-orchestration, durable-execution, human-in-the-loop, multi-agent, langchain-ecosystem, stateful-agents, ai-agents, retrieval-augmented-generation

## Member repositories
- langchain-ai/langgraph (main) score 91

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:08.246001+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:24:03.926615+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/langgraph (fetched 2026-08-28T04:12:08.246001+00:00, sha 2bac3ea9f741)
  - homepage: https://docs.langchain.com/oss/python/langgraph/ (fetched 2026-08-29T07:46:37.309276+00:00, sha 154261570bc3)
  - site_page: https://docs.langchain.com/ (fetched 2026-08-29T07:46:37.312352+00:00, sha e6cbe67a291c)
  - site_page: https://docs.langchain.com/oss/python/integrations/providers/overview (fetched 2026-08-29T07:46:37.314058+00:00, sha 8260e6c475ce)
  - site_page: https://docs.langchain.com/oss/python/langgraph/install (fetched 2026-08-29T07:46:37.316331+00:00, sha 311630398b55)
  - site_page: https://docs.langchain.com/oss/python/langgraph/quickstart (fetched 2026-08-29T07:46:37.318319+00:00, sha edb32dc646c6)
  - site_page: https://docs.langchain.com/oss/python/releases/changelog (fetched 2026-08-29T07:46:37.320458+00:00, sha 048dded673bc)
  - site_page: https://docs.langchain.com/langsmith/trace-with-langchain (fetched 2026-08-29T07:46:37.322526+00:00, sha 32a7ec425016)
  - site_page: https://docs.langchain.com/use-these-docs (fetched 2026-08-29T07:46:37.325130+00:00, sha 5ab7220bb555)
  - registry_pypi: https://pypi.org/pypi/langgraph/json (fetched 2026-08-29T07:46:37.336725+00:00, sha 9ea577abe39a)
- Data as of 2026-08-30T08:39:29.467469+00:00.