LangGraph
Build resilient agents.
LangGraph scores 7.5/10 (Strong) in Agent Frameworks.
Language Python License MIT Stars 36.4k★ Type library Self-host Yes Repo langchain-ai/langgraph Homepage https://www.langchain.com/langgraph
Quality
Strong 7.5
Adoption 64
Activity 79
Maturity 96
Community 70
Capability 43
Show the math
Overall 7.5/10
value = 7.5/10
score = value
Adoption 6.8/10
value = 64/100
score = 1 + 9 * value / 100
Activity 8.1/10
value = 78.8/100
score = 1 + 9 * value / 100
Maturity 9.6/10
value = 95.6/100
score = 1 + 9 * value / 100
Community 7.3/10
value = 69.9/100
score = 1 + 9 * value / 100
Capability 4.9/10
value = 43.4/100
score = 1 + 9 * value / 100
Key metrics
36.4k★ GitHub stars
288/90d Recent commits
13 devs/90d Recent contributors
DR Bench 0.4344 Deep Research Bench (RACE) LangChain's Open Deep Research, built on LangGraph, achieved an overall RACE score of 0.4344 (43.44%) on Deep Research Bench (100 PhD-level research tasks), ranking #6 on the leaderboard. Mapped to the langgraph slug since the agent is built on LangGraph. Source: langchain-ai/open_deep_research README. https://github.com/langchain-ai/open_deep_research
2.9y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
python stateful graph multi-agent workflow