managed-deepagents 0.1.2

Python SDK for LangSmith Managed Deep Agents.

managed-deepagents

Python SDK for the LangSmith Managed Deep Agents API.

Managed Deep Agents is a hosted runtime for creating, running, and operating Deep Agents through LangSmith. This package is currently public beta software.

Installation

pip install managed-deepagents

Requirements:

• Python 3.10 or newer
• A LangSmith API key with access to Managed Deep Agents

Configuration

The client reads LANGSMITH_API_KEY by default.

export LANGSMITH_API_KEY="..."

The default API URL is https://api.smith.langchain.com/v1/deepagents. You can override it with LANGSMITH_ENDPOINT or the api_url client option.

Quickstart

from managed_deepagents import Client

with Client() as client:
    agent = client.agents.create(
        name="research-assistant",
        model="openai:gpt-5.5",
        instructions="You are a careful research assistant.",
    )

    thread = client.threads.create(agent_id=agent["id"])

    for event in client.threads.stream(
        thread["id"],
        agent_id=agent["id"],
        messages=[{"role": "user", "content": "Summarize the latest notes."}],
        stream_mode=["values", "updates", "messages-tuple"],
    ):
        print(event.event, event.data)

Async Usage

from managed_deepagents import AsyncClient

async with AsyncClient() as client:
    agent = await client.agents.create(
        name="research-assistant",
        model="openai:gpt-5.5",
        instructions="You are a careful research assistant.",
    )

Agent Files

Top-level files entries may be passed as raw strings; the SDK normalizes them to file entries before sending the request. Use either instructions or files["AGENTS.md"], not both, because the API maps the typed prompt field to AGENTS.md.

agent = client.agents.create(
    name="research-assistant",
    files={
        "AGENTS.md": "You are a careful research assistant.",
        "skills/research/SKILL.md": "# Research\n\nGather context before answering.",
    },
    include_files=True,
)

API Surface

Resources exposed by the client:

• client.agents: list, create, get, update, delete, clone, health
• client.threads: list, create, search, count, get, update, delete, create run, invoke, stream, bulk update, resolve interrupt
• client.mcp_servers: create, list, get, update, delete, register OAuth provider, list tools
• client.auth_sessions: create and get

Errors

from managed_deepagents import ManagedDeepAgentsAPIError

try:
    client.agents.get("missing-agent")
except ManagedDeepAgentsAPIError as error:
    print(error.status_code, error.code, error.detail)

Links

• Repository: https://github.com/langchain-ai/managed-deepagents-sdk
• Issues: https://github.com/langchain-ai/managed-deepagents-sdk/issues
• Changelog: https://github.com/langchain-ai/managed-deepagents-sdk/blob/main/CHANGELOG.md