Open Agent Spec

This page covers all LangChain integrations with Open Agent Specification.

Open Agent Spec is a framework-agnostic declarative language from Oracle for defining agentic systems. It allows to define agents and workflows in a portable JSON/YAML format that can be executed across different runtimes.

Installation and setup

You can refer to the installation guide to install pyagentspec.

You can subsequently install the LangGraph Adapter through its extra dependency:

pip install "pyagentspec[langgraph]"

LangGraph Adapter

The LangGraph Adapter allows for instantiation and execution of Open Agent Spec configurations using LangGraph. The AgentSpecLoader class is responsible for loading Agent Spec configurations (in JSON or YAML format) and instantiating them as runnable agents within the LangGraph environment. It also includes support for mapping of declared tools to corresponding Python functions.

The following example shows the creation of a simple Agent Spec Agent and its conversion into a LangGraph assistant. Starting from the Agent Spec Agent creation:

# Create a Agent Spec agent
from pyagentspec.agent import Agent
from pyagentspec.llms.openaicompatibleconfig import OpenAiCompatibleConfig
from pyagentspec.property import FloatProperty
from pyagentspec.tools import ServerTool

subtraction_tool = ServerTool(
    name="subtraction-tool",
    description="subtract two numbers together",
    inputs=[FloatProperty(title="a"), FloatProperty(title="b")],
    outputs=[FloatProperty(title="difference")],
)

agentspec_llm_config = OpenAiCompatibleConfig(
    name="llama-3.3-70b-instruct",
    model_id="/storage/models/Llama-3.3-70B-Instruct",
    url="url.to.my.llm",
)

agentspec_agent = Agent(
    name="agentspec_tools_test",
    description="agentspec_tools_test",
    llm_config=agentspec_llm_config,
    system_prompt="Perform subtraction with the given tool.",
    tools=[subtraction_tool],
)

The Agent can be subsequently exported to JSON:

# Export the Agent Spec configuration
from pyagentspec.serialization import AgentSpecSerializer

agentspec_config = AgentSpecSerializer().to_json(agentspec_agent)

And converted into a LangGraph assistant using AgentSpecLoader. The example also showcases the mapping of the tool and the execution of a conversation.

# Load and run the Agent Spec configuration with LangGraph
from pyagentspec.adapters.langgraph import AgentSpecLoader

def subtract(a: float, b: float) -> float:
    return a - b

async def main():
    loader = AgentSpecLoader(tool_registry={"subtraction-tool": subtract})
    assistant = loader.load_json(agentspec_config)

    while True:
        user_input = input("USER >> ")
        if user_input == "exit":
            break
        result = await assistant.ainvoke(
            input={"messages": [{"role": "user", "content": user_input}]},
        )
        print(f"AGENT >> {result['messages'][-1].content}")

---

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.