langgraph-prebuilt

Library with high-level APIs for creating and executing LangGraph agents and tools.

langgraph-prebuilt Permissive license MIT Active ★ 39,627 v1.1.0 released 2026-05-12

Install

langgraph-prebuilt on PyPI

pip

pip install langgraph-prebuilt

uv

uv add langgraph-prebuilt

poetry

poetry add langgraph-prebuilt

Package facts

License	MIT (permissive)
Python support	supports the current Python release (>=3.10)
Install friction	low — pure-Python wheel
Runtime dependencies	2 — langchain-core, langgraph-checkpoint
Maintenance	actively maintained — 93 days since the last release
Last repo commit	2026-08-12
First released	2025-02-27
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: langgraph_prebuilt-1.1.0-py3-none-any.whl

Development Status :: 5 - Production/StableProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: Implementation :: CPythonProgramming Language :: Python :: Implementation :: PyPy

About langgraph-prebuilt

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

LangGraph Prebuilt

This library defines high-level APIs for creating and executing LangGraph agents and tools.

> [!IMPORTANT] > This library is meant to be bundled with langgraph, don't install it directly

Agents

langgraph-prebuilt provides an implementation of a tool-calling ReAct-style agent - create_react_agent:

pip install langchain-anthropic

```python from langchain_anthropic import ChatAnthropic from langgraph.prebuilt import create_react_agent

Define the tools for the agent to use

def search(query: str): """Call to surf the web.""" # This is a placeholder, but don't tell the LLM that... if "sf" in query.lower() or "san francisco" in query.lower(): return "It's 60 degrees and foggy." return "It's 90 degrees and sunny."

tools = [search] model = ChatAnthropic(model="claude-3-7-sonnet-latest")

app = create_react_agent(model, tools)

run the agent

app.invoke( {"messages": [{"role": "user", "content":...

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

Provides high-level APIs for building LangGraph agents and tools, including a ReAct-style agent implementation, tool execution nodes, and validation nodes for agentic workflows.

Low install friction with only two runtime dependencies (langchain-core, langgraph-checkpoint). Active maintenance with recent releases and a well-starred repository.

MIT license permits commercial and private use with minimal restrictions, making it suitable for most projects.

Usage

pip install langgraph-prebuilt
from langgraph.prebuilt import create_react_agent

app = create_react_agent(model, tools=[your_tool])
app.invoke({"messages": [{"role": "user", "content": "query"}]})

Requires Python 3.10 or later. The documentation notes this library is meant to be bundled with langgraph rather than installed directly.

Verdict: A production-ready, actively maintained library for building agentic workflows with LangGraph. Low dependency overhead, permissive MIT license, and no known vulnerabilities make it a solid choice for agent development—though the bundling note suggests verifying compatibility with your langgraph version.

Needs verification

Whether installing langgraph-prebuilt directly (rather than via langgraph) is supported or recommended in current versions
Specific compatibility matrix between langgraph-prebuilt 1.1.0 and langgraph versions
Whether external LLM provider packages are required at runtime for the usage examples shown

langgraph agent prebuiltreact agent implementationtool node executoragentic workflow componentstool validation nodelanggraph prebuilt agentsagent tool calling