# LangGraph

> Framework for stateful, multi-step agent graphs.

LangGraph has a SharkScore of 71.3/100, ranked #18 of 665 in Frameworks & SDKs (updated 2026-11-19).

- Website: https://www.langchain.com/langgraph (langchain.com)
- Kind: Tool · Pricing: Open source
- Maker: LangChain
- Repository: https://github.com/langchain-ai/langgraph
- Categories: Frameworks & SDKs, Agents & automation
- Verified by the maker: no

## Why it scores 71.3

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 65 | 30% |
| User reviews | no data | 25% |
| Maintenance | 100 | 20% |
| Trust & transparency | 60 | 15% |
| Momentum | no data | 10% |

Evidence covers 87% of the score's weight. Compared with other listings in Frameworks & SDKs.

## Evidence

| Signal | Value |
|---|---|
| Traffic rank (Tranco) | — |
| GitHub stars | 45.1K |
| Stars, last 90 days | — |
| Downloads, 30 days | 81M |
| Reviews | none yet |
| Last update | 0 days ago |
| Uptime, 30 days | 100.0% |
| Public pricing / Free tier / API / MCP | yes / yes / no / no |

## RankShark review

Automated evaluation by RankShark · 2026-11-18 · method review-1.0 · https://rankshark.pro/how-we-review
We were not paid for this review.

As of 2026-11-18, LangGraph is a free, MIT-licensed open-source framework for building agent workflows with low-level control. [E1]

LangGraph is an agent runtime and low-level orchestration framework. The vendor describes it as a way to build customizable agents and workflows, including single-agent, multi-agent, and hierarchical designs. [E1]

### Pros

- Supports several workflow patterns, including single-agent, multi-agent, and hierarchical designs.
- Includes vendor-described options for human review, conversation memory, and token-by-token streaming.
- The vendor says the open-source library is free to use under the MIT license.

### Cons

- The listed managed deployment option is LangSmith Agent Server, available in LangSmith Plus and Enterprise; the evidence does not state LangGraph-specific deployment pricing.
- No public prices found on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.

### Pricing

No public prices found on the pages we checked (2026-11-18).

### Sources

- https://www.langchain.com/langgraph (fetched 2026-11-18)
- https://www.langchain.com/pricing (fetched 2026-11-18)
- https://docs.langchain.com/ (fetched 2026-11-18)
- https://docs.langchain.com/langsmith/changelog (fetched 2026-11-18)
- https://www.langchain.com/privacy-policy (fetched 2026-11-18)
- https://www.langchain.com/terms-of-service (fetched 2026-11-18)
- https://trust.langchain.com/ (fetched 2026-11-18)

## Top alternatives

1. [Model Context Protocol](https://rankshark.pro/tools/model-context-protocol) — SharkScore 81.7. Open protocol and SDKs that connect AI apps to tools and data.
2. [AI SDK](https://rankshark.pro/tools/ai-sdk) — SharkScore 77.7. TypeScript toolkit for building AI apps and agents.
3. [LangChain](https://rankshark.pro/tools/langchain) — SharkScore 77.7. Build agents and LLM apps in Python and TypeScript.
4. [LangSmith](https://rankshark.pro/tools/langsmith) — SharkScore 76.9. Tracing, evaluation and monitoring for LLM apps.
5. [Transformers](https://rankshark.pro/tools/transformers) — SharkScore 76.9. Hugging Face's library of pretrained models for text, vision and audio.

---
Source: https://rankshark.pro/tools/langgraph · Method v2026-11-18.2: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
