Repolode
langchain-ai

langchain-ai/social-media-agent

An AI agent that turns a URL into draft Twitter and LinkedIn posts, with human approval before publishing, built on LangGraph.

Open-source alternative to:HootsuiteBuffer

Stars
2,922
Forks
531
Open issues
19
Last commit
yesterday

What is it?

Social Media Agent takes a URL, reads its content, and generates a Twitter or LinkedIn post based on it. The agent runs as a LangGraph server and pauses at points where a person must act through a human-in-the-loop flow: handling platform authentication, editing the draft, and accepting or rejecting the post.

Supporting services are pluggable. Firecrawl handles web scraping, Arcade or your own developer accounts handle authorization and posting, and Supabase stores images. Optional integrations cover GitHub repository URLs, YouTube content through Google Vertex AI, and Slack channels that feed links into the agent via cron jobs.

The prompts are written for LangChain's products, but the business context, example posts, structure instructions and content rules can be replaced to fit another brand or subject.

Key features

  • 01Generates Twitter and LinkedIn posts from a given URL
  • 02Human-in-the-loop review to edit, accept or reject drafts
  • 03Web scraping through Firecrawl, with GitHub and YouTube content parsing in the full setup
  • 04Posting via Arcade authorization or your own Twitter and LinkedIn developer apps
  • 05Image uploads stored in Supabase
  • 06Optional Slack ingestion and cron-based scheduling

Use cases

  • Turning blog posts or release notes into social media drafts for a marketing team
  • Collecting links submitted in a Slack channel and generating posts from them daily
  • Adapting the prompts and examples to create posts for a different brand or topic

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/langchain-ai/social-media-agent.git
  2. 2

    Install dependencies

    yarn install
  3. 3

    Copy the quickstart env file to .env and add your API keys

    cp .env.quickstart.example .env
  4. 4

    Start the LangGraph server

    yarn langgraph:in_mem:up

Things to know

  • Basic setup needs several third-party API keys, including Anthropic, FireCrawl and Arcade.
  • Basic setup lacks GitHub, Twitter and YouTube URL parsing, Slack integration, and image uploads.

Topics

FAQ

What is social-media-agent?
An AI agent that turns a URL into draft Twitter and LinkedIn posts, with human approval before publishing, built on LangGraph. Social Media Agent takes a URL, reads its content, and generates a Twitter or LinkedIn post based on it. The agent runs as a LangGraph server and pauses at points where a person must act through a human-in-the-loop flow: handling platform authentication, editing the draft, and accepting or rejecting the post.
Is social-media-agent free to use? What license does it have?
social-media-agent is open source under the MIT license. Check the license terms before using it in commercial products.
Is social-media-agent still maintained?
Actively maintained. The last commit to social-media-agent was on Oct 19, 2026.
What can I use social-media-agent for?
Turning blog posts or release notes into social media drafts for a marketing team Collecting links submitted in a Slack channel and generating posts from them daily Adapting the prompts and examples to create posts for a different brand or topic
How do I install social-media-agent?
Clone the repository: git clone https://github.com/langchain-ai/social-media-agent.git Install dependencies: yarn install Copy the quickstart env file to .env and add your API keys: cp .env.quickstart.example .env Start the LangGraph server: yarn langgraph:in_mem:up
Where can I get social-media-agent?
The source code and installation instructions are on GitHub: https://github.com/langchain-ai/social-media-agent

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects