langchain-ai/langgraph
The most adopted graph-based agent orchestration framework: workflows as explicit state machines with checkpointing, human-in-the-loop gates, and durable execution. Agentiquette scores it 82/100 (A-tier), methodology v1.0, scored 2026-07-07.
Key facts
| Category | Orchestration framework |
|---|---|
| License | MIT |
| Maintainer | LangChain |
| Compatible agents | generic |
| File patterns | |
| Triggering | manual-reference |
| GitHub metrics | 36,686 stars · 6,156 forks · 602 open issues (fetched 2026-07-07) |
| Last commit | 2026-07-06 |
| Created | 2023-08-09 |
Editorial analysis
The strongest argument in the orchestration class that loops should be data structures, not vibes: state, edges, checkpoints, and interrupts are all first-class and inspectable. Checkpoint-resume and human-gate patterns documented on this site have their most complete industrial implementation here. The cost is ceremony, which is real but honest.
Risks
Graph explicitness is a floor and a ceiling: simple tasks carry framework overhead, and the LangChain ecosystem's churn history warrants version pinning.
Evidence notes: Reliability: explicit state transitions, native checkpointing, resumability tested in docs examples we ran. Eval readiness: graph structure makes runs replayable. Safety: interrupts and gates exist; permissions are the host's problem.
Install and first run
pip install langgraphAlternatives in this category
An agent framework built on type validation: structured outputs, dependency injection, and tool schemas checked the way Pydantic checks…
OpenAI's first-party multi-agent framework: agents, handoffs, guardrails, and tracing in a deliberately small API surface.
Google's Agent Development Kit: code-first agent construction with built-in evaluation tooling and deployment paths into the Google Cloud…
Compare with pydantic-ai · Compare with openai-agents-python
Embed this badge
Maintainers of scored entries can embed their live badge; it updates when the score does and links back to this page.
[](https://agentiquette.com/index/repos/langgraph)Frequently asked questions
Is langchain-ai/langgraph good?
langchain-ai/langgraph scores 82/100 (A-tier) on Agentiquette's methodology v1.0, scored 2026-07-07. Strengths and weaknesses are in the editorial analysis; the score is explained dimension by dimension in the scorecard.
What is langchain-ai/langgraph for?
The most adopted graph-based agent orchestration framework: workflows as explicit state machines with checkpointing, human-in-the-loop gates, and durable execution.
Is langchain-ai/langgraph maintained?
Last commit 2026-07-06, 602 open issues at fetch time (2026-07-07). Maintenance is scored at 92 of 100.
Maintainer of langchain-ai/langgraph? Claim this listing and suggest corrections.