Linkedin Saved Posts Ai
What is Linkedin Saved Posts Ai
linkedin-saved-posts-ai is a tool designed to scrape, classify, and interact with your LinkedIn saved posts using technologies like Supabase, pgvector, Vercel Edge Functions, Playwright MCP, and OpenRouter with OpenAI LLMs.
Use cases
Use cases include organizing and retrieving saved LinkedIn posts efficiently, engaging in conversations about saved content with an AI assistant, and automating the synchronization of saved posts for ongoing analysis.
How to use
To use linkedin-saved-posts-ai, clone the repository from GitHub, set up your environment variables, install the necessary dependencies, and run the application locally. Access it via a web browser at http://localhost:3000 and log in using Supabase Email-Link Auth.
Key features
Key features include a one-time bootstrap scrape of saved posts, daily incremental sync, a structured taxonomy for filtering, fast vector and full-text search, a chat assistant with multiple AI models, optional enrichment for external links, and structured code generation.
Where to use
linkedin-saved-posts-ai can be used in fields such as social media management, content curation, data analysis, and AI-driven chat applications, particularly for professionals who utilize LinkedIn for networking and information gathering.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Linkedin Saved Posts Ai
linkedin-saved-posts-ai is a tool designed to scrape, classify, and interact with your LinkedIn saved posts using technologies like Supabase, pgvector, Vercel Edge Functions, Playwright MCP, and OpenRouter with OpenAI LLMs.
Use cases
Use cases include organizing and retrieving saved LinkedIn posts efficiently, engaging in conversations about saved content with an AI assistant, and automating the synchronization of saved posts for ongoing analysis.
How to use
To use linkedin-saved-posts-ai, clone the repository from GitHub, set up your environment variables, install the necessary dependencies, and run the application locally. Access it via a web browser at http://localhost:3000 and log in using Supabase Email-Link Auth.
Key features
Key features include a one-time bootstrap scrape of saved posts, daily incremental sync, a structured taxonomy for filtering, fast vector and full-text search, a chat assistant with multiple AI models, optional enrichment for external links, and structured code generation.
Where to use
linkedin-saved-posts-ai can be used in fields such as social media management, content curation, data analysis, and AI-driven chat applications, particularly for professionals who utilize LinkedIn for networking and information gathering.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
LinkedIn Saved Posts AI
Scrape, classify & chat over your LinkedIn Saved Posts using Supabase + pgvector, Vercel Edge Functions, Playwright MCP, Firecrawl MCP, and OpenRouter LLMs.
✨ Features
- One-time bootstrap scrape of every saved post (≈ 400 posts)
- Daily incremental sync via Vercel cron (stops on first duplicate)
- Rigid Topic → Category → Subcategory taxonomy for clean filtering
- Fast vector & full-text search (pgvector + Postgres)
- Chat assistant with switchable models:
o4-mini-high,o4-mini,gpt-4.1,gemini-2.5-flash - Firecrawl enrichment for external links (optional)
- Cursor AI rule-files for structured, SOLID, KISS code generation
🏗 Stack
| Layer | Tech |
|---|---|
| Front-end | Next.js (App Router), Tailwind, shadcn/ui |
| Back-end | Vercel Edge Functions + Playwright MCP |
| Database | Supabase Postgres + pgvector |
| AI / LLM | OpenRouter (OpenAI & Gemini models) |
| Agents | MCP Servers (playwright, firecrawl, tavily, git, github, sequential-thinking, memory) |
🚀 Quick Start
git clone https://github.com/BjornMelin/linkedin-saved-posts-ai.git
cd linkedin-saved-posts-ai
cp .env.example .env.local # add your keys + LinkedIn li_at cookie
pnpm install
pnpm dev # local Next.js + Supabase
Then open http://localhost:3000 and log in with Supabase Email-Link Auth.
🛡 Security Notes
Secrets stay only in Vercel’s encrypted env-store — never commit them.
GitHub secret-scanning is active for public repos. If a secret leaks, rotate immediately.
📄 License
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
