langgraph-sdk

Install

langgraph-sdk on PyPI

pip install langgraph-sdk

uv add langgraph-sdk

poetry add langgraph-sdk

Package facts

Evidence: langgraph_sdk-0.4.2-py3-none-any.whl

About langgraph-sdk

from the package's own PyPI description — quoted content, verbatim

pip install -U langgraph-sdk

from langgraph_sdk import get_client

# If you're using a remote server, initialize the client with `get_client(url=REMOTE_URL)`
client = get_client()

# List all assistants
assistants = await client.assistants.search()

# We auto-create an assistant for each graph you register in config.
agent = assistants[0]

# Start a new thread
thread = await client.threads.create()

# Start a streaming run
input = {"messages": [{"role": "human", "content": "what's the weather in la"}]}
async for chunk in client.runs.stream(thread['thread_id'], agent['assistant_id'], input=input):
    print(chunk)

Read as markdown · JSON record · Source repository

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

Python SDK for interacting with the LangGraph API, providing async-first client access to assistants, threads, and streaming run execution.

Low friction; pure Python wheel with five runtime dependencies (httpx, langchain-core, langchain-protocol, orjson, websockets). Active maintenance with latest release 73 days ago and 39627 GitHub stars.

MIT license permits unrestricted use, modification, and distribution in both open and proprietary projects with minimal attribution requirements.

pip install -U langgraph-sdk

from langgraph_sdk import get_client

client = get_client()
assistants = await client.assistants.search()
thread = await client.threads.create()
async for chunk in client.runs.stream(thread['thread_id'], assistants[0]['assistant_id'], input={"messages": [{"role": "human", "content": "hello"}]}):
    print(chunk)

Verdict: Well-maintained, permissively licensed SDK with low install friction and no known vulnerabilities. Suitable for agentic workflows if you have a LangGraph API deployment available.

Needs verification

• Whether localhost:8123 endpoint is always available or requires explicit langgraph-cli setup.
• Performance characteristics and throughput limits for high-concurrency thread streaming.
• Backward compatibility guarantees across minor versions given active development status.

Similar packages