What is LangGraph?
A framework for building stateful, multi-step AI agent workflows as graphs. Built on top of LangChain for complex agentic applications.
Searching X (Twitter) with LangGraph
This integration lets your LangGraph agent search X (Twitter) in real time via the Scavio API. The agent gets back structured JSON with post text, author handles, created_at timestamps, favorites, retweets, replies, quotes -- ready for reasoning and decision-making.
Setup
Bash
pip install langgraph langchain-scavio langchain-openaiCode Example
Here is a complete LangGraph agent that searches X (Twitter) using Scavio:
Python
from langgraph.prebuilt import create_react_agent
from langchain_scavio import ScavioSearch
from langchain_openai import ChatOpenAI
tool = ScavioSearch(scavio_api_key="sk_live_your_key")
llm = ChatOpenAI(model="gpt-5.5")
agent = create_react_agent(llm, [tool])
result = agent.invoke({
"messages": [{"role": "user", "content": "Search X (Twitter) for AI agents"}]
})
print(result["messages"][-1].content)Full Working Example
A production-ready example with error handling:
Python
"""
LangGraph agent that queries X (Twitter) via Scavio.
ScavioSearch calls POST /api/v1/x/search under the hood.
"""
import os
from langgraph.prebuilt import create_react_agent
from langchain_scavio import ScavioSearch
from langchain_openai import ChatOpenAI
os.environ.setdefault("SCAVIO_API_KEY", "sk_live_your_key")
tool = ScavioSearch()
llm = ChatOpenAI(model="gpt-5.5")
agent = create_react_agent(llm, [tool])
result = agent.invoke({
"messages": [{"role": "user", "content": "Search X (Twitter) for AI agents"}]
})
for message in result["messages"]:
if hasattr(message, "content") and message.content:
print(message.type, str(message.content)[:200])Pricing
Scavio offers a free tier with 50 credits on signup (1 credit per search). No credit card required. This is enough to build and test your LangGraph integration. Paid plans start at $30/month for higher volumes.