# langchain-ai/langgraph-supervisor-py

Repository: https://github.com/langchain-ai/langgraph-supervisor-py
Canonical: https://ross.abutalabs.com/products/langgraph-supervisor-py
Language: Python
License: MIT
License Family: permissive
Last push: 2026-07-15T06:32:54+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 57, longevity 41
- inputs: {"age_days": 574, "days_push": 49, "days_rel": 287, "gap_med": 4, "n_releases_24m": 28}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1646, forks 256 (observed 2026-08-28T04:05:16.515264+00:00)

## What it is
A Python library for building hierarchical multi-agent systems on top of LangGraph, where a central supervisor agent orchestrates and delegates tasks to specialized agents via tool-based handoffs. It supports streaming, memory, and human-in-the-loop workflows, though the maintainers now recommend the manual supervisor pattern for most use cases.

## Use cases
- orchestrate multiple specialized AI agents with a supervisor
- build a hierarchical multi-agent system in Python
- delegate tasks between LLM agents automatically
- route user requests to the right expert agent
- coordinate research and math agents in one workflow
- add human-in-the-loop approval to multi-agent pipelines

## When to choose
- you already use LangGraph and want a ready-made supervisor orchestration layer
- you need hierarchical agent coordination with tool-based handoffs
- you're maintaining an existing codebase built on this library and upgrading to LangChain 1.0

## When to avoid
- you're starting a new project - the maintainers recommend implementing the supervisor pattern directly via tools
- you need fine-grained control over context engineering that a library abstraction would hide
- your use case involves only a single agent

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

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:16.515264+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 2026-08-30T03:45:23.237835+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/langgraph-supervisor-py (fetched 2026-08-28T04:05:16.515264+00:00, sha 6ed02d18d6d5)
- Data as of 2026-08-30T08:39:29.467469+00:00.