This repository provides a public starter pack of Lenny's Newsletter posts and Podcast transcripts, formatted in AI-friendly markdown. It aims to inspire developers and researchers to build applications using this unique dataset, offering a curated collection for easy integration with AI tools.

How It Works

The project archives content as plain markdown files, organized into newsletters/ and podcasts/ directories. A central index.json file provides metadata for each entry, including titles, dates, word counts, and guest information. This structure facilitates straightforward parsing and utilization by AI models and development tools.

Quick Start & Requirements

Clone the repository using git clone https://github.com/LennysNewsletter/lennys-newsletterpodcastdata.git. Alternatively, a ZIP archive of the starter pack can be downloaded from https://www.lennysdata.com after signing in. Access to the full archive and additional features requires a paid subscription via https://www.lennysdata.com.

Highlighted Details

• The free starter pack includes 10 newsletter posts and 50 podcast transcripts.
• A paid archive offers 349 newsletter posts and 289 podcast transcripts, along with full MCP access and a private GitHub repository.
• Numerous example projects demonstrate creative uses of the data, ranging from AI agents answering product advice to visual infographic summaries.

Maintenance & Community

The primary hub for accessing the full dataset, MCP features, and subscription information is https://www.lennysdata.com. Specific community channels or contributor details are not detailed in the provided README.

Licensing & Compatibility

Usage terms are detailed in LICENSE.md. The plain markdown format ensures broad compatibility with various AI tools and development workflows. Specific restrictions for commercial use or closed-source linking would be outlined in the license file.

Limitations & Caveats

The public repository serves as a limited starter pack; the complete dataset requires a paid subscription. Additionally, newsletter posts published within the last three months are intentionally excluded from the archive.