A self-improving AI agent that creates and refines skills from experience, runs on many model providers, and works through CLI and messaging apps.
- 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
Clone the repository
git clone https://github.com/langchain-ai/social-media-agent.git - 2
Install dependencies
yarn install - 3
Copy the quickstart env file to .env and add your API keys
cp .env.quickstart.example .env - 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
Self-hosted control center for running coding agents like OpenHands, Claude Code and Codex across local, remote and cloud backends.
Open source autonomous coding agent that runs as an IDE extension, terminal CLI, desktop app, or SDK.
An open source, general-purpose AI agent that runs on your machine as a desktop app, CLI, or embeddable API, for code and non-code tasks.
A TypeScript SDK for building agent-native apps with generative UI, shared state, and human-in-the-loop flows in React, Angular, Vue, and chat apps.
An open-source coding-agent CLI that runs in the terminal and works with cloud APIs and local model backends like Ollama.