🧠LangGraph
langchain-ai/langgraph · homepage ↗
Build resilient agents.
⭐ Very popular: 40k stars, gaining about 501 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- Graph-Based Architecture: Facilitates the creation of agents with loops, branches, and conditional logic, surpassing traditional DAG limitations.
- Stateful Workflows: Maintains context across long-running processes, essential for applications like chatbots and multi-step tasks.
- Human-in-the-Loop Support: Allows for pauses and interventions, enabling human oversight and adjustments during agent execution.
under the hood
- Built in Python, drawing inspiration from frameworks like NetworkX for its public interface.
- Supports streaming outputs, enabling real-time feedback during agent execution.
- Trusted by companies like Klarna, Replit, Elastic, and Uber for building production-ready AI agents.
our take from PR#11, 2025-06-25
star history
- PR#11 15k 2025-06-25
- now 40k + 25k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Output and attention are roughly in balance.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Build Resilient Language Agents as Graphs
similar projects
compare these →- ⚡ VoltAgent
TypeScript · leaner, 10k stars
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
10k ACTIVE - 📚 Haystack
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
26k ACTIVE - 🦌 DeerFlow
2× the stars
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
80k ACTIVE
comments
Sign in with GitHub to add your blip on LangGraph.