This toolkit contains tools that enable an LLM agent to interact with Twitter (X). The toolkit provides a wrapper around the Twitter (X) API, allowing agents to perform social operations like posting text.
- Node.js 18 or higher
- OpenAI API Key
- Twitter (X) App Developer Keys
npm install @coinbase/twitter-langchain
Set the following environment variables:
export OPENAI_API_KEY=<your-openai-api-key>
export TWITTER_API_KEY=<your-api-key>
export TWITTER_API_SECRET=<your-api-secret>
export TWITTER_ACCESS_TOKEN=<your-access-token>
export TWITTER_ACCESS_TOKEN_SECRET=<your-access-token-secret>
import { TwitterAgentkit } from "@coinbase/cdp-agentkit-core";
import { TwitterToolkit } from "@coinbase/twitter-langchain";
// Initialize Twitter AgentKit
const agentkit = new TwitterAgentkit();
// Create toolkit
const toolkit = new TwitterToolkit(agentkit);
// Get available tools
const tools = toolkit.getTools();
The toolkit provides the following tools:
- account_details - Get the authenticated account details
- account_mentions - Get mentions for a specified account
- post_tweet - Post a tweet to the account
- post_tweet_reply - Post a reply to a tweet on Twitter
npm install @langchain/langgraph @langchain/openai
import { ChatOpenAI } from "@langchain/openai";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
// Initialize LLM
const model = new ChatOpenAI({
model: "gpt-4o-mini",
});
// Create agent executor
const agent = createReactAgent({
llm: model,
tools,
});
// Example usage
const result = await agent.invoke({
messages: [new HumanMessage("please post 'hello, world!' to twitter")],
});
console.log(result.messages[result.messages.length - 1].content);
Check out examples/
for inspiration and help getting started:
- Chatbot: Interactive chatbot with Twitter (X) capabilities
See CONTRIBUTING.md for detailed setup instructions and contribution guidelines.
Apache-2.0