# langchain-ai/langgraph-swarm-py

For your multi-agent needs

Repository: https://github.com/langchain-ai/langgraph-swarm-py
Canonical: https://ross.abutalabs.com/products/langgraph-swarm-py
Homepage: https://langchain-ai.github.io/langgraph/concepts/multi_agent/
Language: Python
License: MIT
License Family: permissive
Topics: agents, langgraph, llms, multiagent, multiagent-systems, python
Last push: 2026-07-15T06:29:47+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 59, longevity 40
- inputs: {"age_days": 560, "days_push": 49, "days_rel": 272, "gap_med": 8, "n_releases_24m": 16}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1558, forks 221 (observed 2026-08-28T04:05:03.466365+00:00)

## What it is
A Python library for building swarm-style multi-agent systems on top of LangGraph, where specialized agents dynamically hand off control to one another. It provides handoff tools, active-agent memory, and integrates with LangGraph's streaming, persistence, and human-in-the-loop features.

## Use cases
- build a multi-agent system where agents hand off to each other
- create specialized LLM agents that collaborate on tasks
- route conversations between expert agents based on user intent
- remember which agent was last active across conversation turns
- add human-in-the-loop and memory to a multi-agent workflow

## When to choose
- you already use LangGraph and want a swarm-style multi-agent architecture
- you need dynamic agent-to-agent handoffs with conversation state persistence
- you want streaming, memory, and human-in-the-loop support out of the box

## When to avoid
- you need a single-agent pipeline without handoffs
- you don't want a dependency on the LangGraph/LangChain ecosystem
- you need a non-Python or framework-agnostic multi-agent solution

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, llm-inference, workflow-automation
- domain: large-language-models, artificial-intelligence
- platform: python
- tags: multi-agent, swarm, handoff, langgraph, llm-orchestration, ai-agents

## Member repositories
- langchain-ai/langgraph-swarm-py (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:03.466365+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 2026-08-30T04:29:54.738047+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/langgraph-swarm-py (fetched 2026-08-28T04:05:03.466365+00:00, sha d50bb36f29ca)
  - homepage: https://langchain-ai.github.io/langgraph/concepts/multi_agent/ (fetched 2026-08-29T11:29:53.554484+00:00, sha 1260f20fe66e)
- Data as of 2026-08-30T08:39:29.467469+00:00.