langgraph-sdk
SDK for interacting with LangGraph API
Decision gist · record as of 2026-08-14
Yes. The package has low install friction, active maintenance, MIT licensing, no known vulnerabilities, and is positioned in the top 1000 PyPI packages by downloads. Install it if you are building applications that interact with LangGraph API servers; skip it if you are only defining graphs locally without a deployment backend.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >=3.10 and a running LangGraph API server (defaults to http://localhost:8123 or requires explicit URL).
- Low friction install with five runtime dependencies.
- Actively maintained as of 2026-08-13 with 39639 repository stars, suggesting stable community adoption.
License · maintenance · safety
MIT (permissive) — MIT license permits unrestricted use, modification, and distribution in both open and proprietary projects.
last release 2026-06-01 (74 days) · last repo commit 2026-08-13 · 39,639 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 57,249,108 downloads/mo, #520 on PyPI
Alternatives
Verify before relying
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)- Whether the package works with LangGraph servers other than those deployed via langgraph-cli.
- Performance characteristics under sustained concurrent streaming with many threads.
- Exact reconnect behavior and error handling when network partitions exceed the 5-attempt limit.
What it is and what it does
LangGraph SDK is a Python client library for interacting with LangGraph API servers, enabling developers to programmatically manage agentic workflows. It provides async-first and sync interfaces for creating assistants, managing conversation threads, and streaming agent execution results in real time.
The package is built on httpx, websockets, and langchain-core, offering both SSE (Server-Sent Events) and WebSocket transports for streaming. It abstracts the REST API layer, allowing developers to focus on orchestrating agent runs rather than managing HTTP details. Thread-centric streaming allows multiple consumers (messages, tool calls, custom events) to share a single connection, reducing overhead in long-lived agent sessions.
Use it for
- Build a chatbot that streams agent responses back to a user interface in real time using async streaming.
- Manage multiple concurrent agent threads for different users or tasks within a single application.
- Consume tool calls and intermediate agent states during execution to implement custom logging or UI updates.
- Deploy agentic workflows via LangSmith and interact with them programmatically from Python applications.
- Implement sync-to-async bridging in existing applications that need to integrate LangGraph agents.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package has low install friction, active maintenance, MIT licensing, no known vulnerabilities, and is positioned in the top 1000 PyPI packages by downloads. Install it if you are building applications that interact with LangGraph API servers; skip it if you are only defining graphs locally without a deployment backend.
Install
langgraph-sdk on PyPI
Before you install
Low friction install with five runtime dependencies. Actively maintained as of 2026-08-13 with 39639 repository stars, suggesting stable community adoption.
Requires Python >=3.10 and a running LangGraph API server (defaults to http://localhost:8123 or requires explicit URL).
License in practice
MIT license permits unrestricted use, modification, and distribution in both open and proprietary projects.
Quickstart
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)Verify before relying
- Whether the package works with LangGraph servers other than those deployed via langgraph-cli.
- Performance characteristics under sustained concurrent streaming with many threads.
- Exact reconnect behavior and error handling when network partitions exceed the 5-attempt limit.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packageshttpxlangchain-corelangchain-protocolorjsonwebsockets |
| Maintenance | Actively maintained 74 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 57,249,108 / month, #520 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: langgraph_sdk-0.4.2-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “langgraph api client”
- langgraph-sdkPython SDK for building and deploying agentic applications via the…
- langchain-mcp-adaptersConverts Anthropic Model Context Protocol (MCP) tools into…
- ag-ui-langgraphBridges LangGraph agent workflows to the AG-UI protocol,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Application Frameworks packages
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Textual is a Python framework for building cross-platform user interfaces that run in the terminal or web browser using a modern, component-based API.
Install it if you're developing CLI tools, dashboards, or interactive terminal applications.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Build and connect to Model Context Protocol servers that expose tools, resources, and prompts to LLM applications over stdio, HTTP, or SSE transports.
Install it if you need to build or connect to servers.
Werkzeug is a WSGI utility library providing request/response objects, URL routing, an interactive debugger, HTTP utilities, and a development server for building web applications.
See also aegra-api · langgraph · langsmith-fetch · langgraph-cli · langgraph-api · ag-ui-langgraph · langgraph-checkpoint · langgraph-runtime-inmem · uipath-langchain · langgraph-prebuilt