| Name | langgraph-supervisor JSON |
| Version |
0.0.1
JSON |
| download |
| home_page | None |
| Summary | An implementation of a supervisor multi-agent architecture using LangGraph |
| upload_time | 2025-02-07 19:00:03 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.11 |
| license | None |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# 🤖 LangGraph Multi-Agent Supervisor
A Python library for creating hierarchical multi-agent systems using [LangGraph](https://github.com/langchain-ai/langgraph). Hierarchical systems are a type of [multi-agent](https://langchain-ai.github.io/langgraph/concepts/multi_agent) architecture where specialized agents are coordinated by a central **supervisor** agent. The supervisor controls all communication flow and task delegation, making decisions about which agent to invoke based on the current context and task requirements.
## Features
- 🤖 **Create a supervisor agent** to orchestrate multiple specialized agents
- 🔄 **Support for both router and orchestrator patterns**
- 🛠️ **Tool-based agent handoff mechanism** for communication between agents
- 📝 **Flexible message history management** for conversation control
This library is built on top of [LangGraph](https://github.com/langchain-ai/langgraph), a powerful framework for building agent applications, and comes with out-of-box support for [streaming](https://langchain-ai.github.io/langgraph/how-tos/#streaming), [short-term and long-term memory](https://langchain-ai.github.io/langgraph/concepts/memory/) and [human-in-the-loop](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/)
## Installation
```bash
pip install langgraph-supervisor
```
## Quickstart
Here's a simple example of a supervisor managing two specialized agents:
```bash
pip install langgraph-supervisor langchain-openai
export OPENAI_API_KEY=<your_api_key>
```
```python
from langchain_openai import ChatOpenAI
from langgraph_supervisor import create_supervisor
from langgraph.prebuilt import create_react_agent
model = ChatOpenAI(model="gpt-4o")
# Create specialized agents
def add(a: float, b: float) -> float:
"""Add two numbers."""
return a + b
def multiply(a: float, b: float) -> float:
"""Multiply two numbers."""
return a * b
def web_search(query: str) -> str:
"""Search the web for information."""
return (
"Here are the headcounts for each of the FAANG companies in 2024:\n"
"1. **Facebook (Meta)**: 67,317 employees.\n"
"2. **Apple**: 164,000 employees.\n"
"3. **Amazon**: 1,551,000 employees.\n"
"4. **Netflix**: 14,000 employees.\n"
"5. **Google (Alphabet)**: 181,269 employees."
)
math_agent = create_react_agent(
model=model,
tools=[add, multiply],
name="math_expert",
prompt="You are a math expert. Always use one tool at a time."
)
research_agent = create_react_agent(
model=model,
tools=[web_search],
name="research_expert",
prompt="You are a world class researcher with access to web search. Do not do any math."
)
# Create supervisor workflow
workflow = create_supervisor(
[research_agent, math_agent],
model=model,
prompt="You are a team supervisor managing a research expert and a math expert.",
)
# Compile and run
app = workflow.compile()
result = app.invoke({
"messages": [
{
"role": "user",
"content": "what's the combined headcount of the FAANG companies in 2024?"
}
]
})
```
## Agent Interaction Patterns
### Orchestrator Pattern
In orchestrator mode (`is_router=False`), agents always return control to the supervisor. The supervisor can then decide who to call next, or respond to the user.
```python
orchestrator = create_supervisor(
[agent1, agent2],
is_router=False,
...
)
```
### Router Pattern
In router mode (`is_router=True`), agents can respond directly to the user. The supervisor just routes the user's message to the appropriate agent.
```python
router = create_supervisor(
[agent1, agent2],
is_router=True,
...
)
```
## Message History Management
You can control how agent messages are added to the overall conversation history of the multi-agent system:
Include full message history from an agent:
```python
workflow = create_supervisor(
agents=[agent1, agent2],
agent_output_mode="full_history"
)
```
Include only the final agent response:
```python
workflow = create_supervisor(
agents=[agent1, agent2],
agent_output_mode="last_message"
)
```
## Multi-level Hierarchies
You can create multi-level hierarchical systems by creating a supervisor that manages multiple supervisors.
```python
research_team = create_supervisor(
[research_agent, math_agent],
model=model,
).compile(name="research_team")
writing_team = create_supervisor(
[writing_agent, publishing_agent],
model=model,
).compile(name="writing_team")
top_level_supervisor = create_supervisor(
[research_team, writing_team],
model=model,
).compile(name="top_level_supervisor")
```
Raw data
{
"_id": null,
"home_page": null,
"name": "langgraph-supervisor",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": "Vadym Barda <19161700+vbarda@users.noreply.github.com >",
"download_url": "https://files.pythonhosted.org/packages/e6/05/702f0d7583fa1d28f6a4936b7e40c9a392fbc6617f0afb353bb50691e142/langgraph_supervisor-0.0.1.tar.gz",
"platform": null,
"description": "# \ud83e\udd16 LangGraph Multi-Agent Supervisor\n\nA Python library for creating hierarchical multi-agent systems using [LangGraph](https://github.com/langchain-ai/langgraph). Hierarchical systems are a type of [multi-agent](https://langchain-ai.github.io/langgraph/concepts/multi_agent) architecture where specialized agents are coordinated by a central **supervisor** agent. The supervisor controls all communication flow and task delegation, making decisions about which agent to invoke based on the current context and task requirements.\n\n## Features\n\n- \ud83e\udd16 **Create a supervisor agent** to orchestrate multiple specialized agents\n- \ud83d\udd04 **Support for both router and orchestrator patterns**\n- \ud83d\udee0\ufe0f **Tool-based agent handoff mechanism** for communication between agents\n- \ud83d\udcdd **Flexible message history management** for conversation control\n\nThis library is built on top of [LangGraph](https://github.com/langchain-ai/langgraph), a powerful framework for building agent applications, and comes with out-of-box support for [streaming](https://langchain-ai.github.io/langgraph/how-tos/#streaming), [short-term and long-term memory](https://langchain-ai.github.io/langgraph/concepts/memory/) and [human-in-the-loop](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/)\n\n## Installation\n\n```bash\npip install langgraph-supervisor\n```\n\n## Quickstart\n\nHere's a simple example of a supervisor managing two specialized agents:\n\n```bash\npip install langgraph-supervisor langchain-openai\n\nexport OPENAI_API_KEY=<your_api_key>\n```\n\n```python\nfrom langchain_openai import ChatOpenAI\n\nfrom langgraph_supervisor import create_supervisor\nfrom langgraph.prebuilt import create_react_agent\n\nmodel = ChatOpenAI(model=\"gpt-4o\")\n\n# Create specialized agents\n\ndef add(a: float, b: float) -> float:\n \"\"\"Add two numbers.\"\"\"\n return a + b\n\ndef multiply(a: float, b: float) -> float:\n \"\"\"Multiply two numbers.\"\"\"\n return a * b\n\ndef web_search(query: str) -> str:\n \"\"\"Search the web for information.\"\"\"\n return (\n \"Here are the headcounts for each of the FAANG companies in 2024:\\n\"\n \"1. **Facebook (Meta)**: 67,317 employees.\\n\"\n \"2. **Apple**: 164,000 employees.\\n\"\n \"3. **Amazon**: 1,551,000 employees.\\n\"\n \"4. **Netflix**: 14,000 employees.\\n\"\n \"5. **Google (Alphabet)**: 181,269 employees.\"\n )\n\nmath_agent = create_react_agent(\n model=model,\n tools=[add, multiply],\n name=\"math_expert\",\n prompt=\"You are a math expert. Always use one tool at a time.\"\n)\n\nresearch_agent = create_react_agent(\n model=model,\n tools=[web_search],\n name=\"research_expert\",\n prompt=\"You are a world class researcher with access to web search. Do not do any math.\"\n)\n\n# Create supervisor workflow\nworkflow = create_supervisor(\n [research_agent, math_agent],\n model=model,\n prompt=\"You are a team supervisor managing a research expert and a math expert.\",\n)\n\n# Compile and run\napp = workflow.compile()\nresult = app.invoke({\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"what's the combined headcount of the FAANG companies in 2024?\"\n }\n ]\n})\n```\n\n## Agent Interaction Patterns\n\n### Orchestrator Pattern\n\nIn orchestrator mode (`is_router=False`), agents always return control to the supervisor. The supervisor can then decide who to call next, or respond to the user.\n\n```python\norchestrator = create_supervisor(\n [agent1, agent2],\n is_router=False,\n ...\n)\n```\n\n### Router Pattern\n\nIn router mode (`is_router=True`), agents can respond directly to the user. The supervisor just routes the user's message to the appropriate agent.\n\n```python\nrouter = create_supervisor(\n [agent1, agent2],\n is_router=True,\n ...\n)\n```\n\n## Message History Management\n\nYou can control how agent messages are added to the overall conversation history of the multi-agent system:\n\nInclude full message history from an agent:\n\n```python\nworkflow = create_supervisor(\n agents=[agent1, agent2],\n agent_output_mode=\"full_history\"\n)\n```\n\nInclude only the final agent response:\n\n```python\nworkflow = create_supervisor(\n agents=[agent1, agent2],\n agent_output_mode=\"last_message\"\n)\n```\n\n## Multi-level Hierarchies\n\nYou can create multi-level hierarchical systems by creating a supervisor that manages multiple supervisors.\n\n```python\nresearch_team = create_supervisor(\n [research_agent, math_agent],\n model=model,\n).compile(name=\"research_team\")\n\nwriting_team = create_supervisor(\n [writing_agent, publishing_agent],\n model=model,\n).compile(name=\"writing_team\")\n\ntop_level_supervisor = create_supervisor(\n [research_team, writing_team],\n model=model,\n).compile(name=\"top_level_supervisor\")\n```",
"bugtrack_url": null,
"license": null,
"summary": "An implementation of a supervisor multi-agent architecture using LangGraph",
"version": "0.0.1",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "9c5984998ebf1077d8369485ea548a7230e4d057ba988ccdb946c981f54d0414",
"md5": "57323182ccaad847e9e616db5c044fee",
"sha256": "910354de37d442d86e69e5d2830feba622f586243f2648aa21ede9fdfb220b3f"
},
"downloads": -1,
"filename": "langgraph_supervisor-0.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "57323182ccaad847e9e616db5c044fee",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 7016,
"upload_time": "2025-02-07T19:00:01",
"upload_time_iso_8601": "2025-02-07T19:00:01.175924Z",
"url": "https://files.pythonhosted.org/packages/9c/59/84998ebf1077d8369485ea548a7230e4d057ba988ccdb946c981f54d0414/langgraph_supervisor-0.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "e605702f0d7583fa1d28f6a4936b7e40c9a392fbc6617f0afb353bb50691e142",
"md5": "727781f1c3330406c7bac003fa9fb688",
"sha256": "cdf7b4f2e68838b96bbb039862e1ccf57623adf408590c10d84033e58ba3d55c"
},
"downloads": -1,
"filename": "langgraph_supervisor-0.0.1.tar.gz",
"has_sig": false,
"md5_digest": "727781f1c3330406c7bac003fa9fb688",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 5555,
"upload_time": "2025-02-07T19:00:03",
"upload_time_iso_8601": "2025-02-07T19:00:03.571859Z",
"url": "https://files.pythonhosted.org/packages/e6/05/702f0d7583fa1d28f6a4936b7e40c9a392fbc6617f0afb353bb50691e142/langgraph_supervisor-0.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-07 19:00:03",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "langgraph-supervisor"
}
