Skip to content

VISHALSARMAH/LinkedIn-AI-Posting-Bot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LinkedIn AI Posting Bot

Overview

This project streamlines the end-to-end workflow for creating and publishing LinkedIn posts from trending AI news.

It automatically:

  • Fetches trending AI news
  • Analyzes and ranks relevance
  • Generates LinkedIn posts using LLMs
  • Validates and improves structure
  • Scores posts using AI
  • Selects the best post
  • Publishes to LinkedIn from local execution (manual login step)

Features

  • Automated news aggregation
  • AI-powered content generation
  • Semantic duplicate filtering
  • Post validation and rewriting
  • AI scoring system
  • LinkedIn posting using Playwright

Tech Stack

  • Python
  • OpenRouter (LLMs)
  • Sentence Transformers (semantic similarity)
  • Playwright (browser automation)

Project Pipeline

News -> Scrape -> Rank -> Filter -> Generate -> Validate -> Score -> Post

Setup Instructions

  1. Clone repo
git clone <your-repo-url>
cd LinkedIn-Automation
  1. Create virtual environment
python -m venv .venv
source .venv/bin/activate
  1. Install dependencies
pip install -r requirements.txt
  1. Set environment variable
export OPENROUTER_API_KEY="your_api_key"
  1. Run
python main.py

Important Notes

  • cookies.json is not included for security.
  • API keys must be set via environment variables.
  • Project runs locally and requires LinkedIn login in the browser.

Future Improvements

  • GitHub Actions automation
  • Scheduled posting
  • Database integration
  • Multi-platform posting

Disclaimer

This project is for educational purposes. Use responsibly and respect LinkedIn's terms.

About

AI-powered LinkedIn posting bot that fetches trending AI news, generates and validates post drafts, ranks the best version, and publishes locally via Playwright with manual login.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages