# Project export: Instant-gram | Social Media Content Generator

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: TreeHacks 2024
- Tagline: InstantGram is an AI agent that generates highly engaging and non-repetitive social media content. InstantGram helps startups and influencers boost social media engagement and expand audiences.
- Devpost: https://devpost.com/software/instant-gram-social-media-content-generator
- GitHub: not linked
- Video: https://www.youtube.com/embed/8Hvu0wu0Qu4?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

InstantGram was born from Wanrong's experience building a consumer product called AI Anywhere. We acquired over 50,000 users without investing in marketing, only through creating social media posts and videos. Although it’s very effective for user acquisition and building customer relationships, we just lacked time and resources to create more content. We interviewed 10+ startup founders and influencers and realized they faced the same issue.

### What it does

InstantGram is an AI agent that creates engaging and non-repetitive social media content for platforms like Twitter, Instagram, and TikTok. It takes input once (information about the social media account) and and generates multiple ready-to-post pieces daily. By utilizing a large language model and incorporating online sources such as social media accounts, news outlets, Medium, and Substack, InstantGram automatically produces trendy content to enhance brand awareness, grow audiences, and drive conversions.

### How we built it

Wanrong developed the logic for the agent, collecting fresh content from multiple sources, conducting research on internet, and creating Instagram posts with captions and multiple slides (text + image). Zubair sourced relevant images for the posts and handled frontend development. Haris designed templates to merge images and text into engaging slides. Ved led the frontend development and auto-posting process using multiple frameworks. Challenges we encountered Initially drawn to a Python frontend framework, we realized it lacked support for desired features. We aimed for automated content posting but discovered that most platforms require a business account to access the auto-posting API. Eventually, we connected our AI agent to a Twitter account. Accomplishments we're proud of Successfully integrating multiple components across various servers and services. Developing a framework that enables automated multi-modal content creation for multiple platforms. And participating in our first hackathon together!

### What we learned

The importance of selecting stable and feature-rich frameworks. Expanding our knowledge of different frameworks and packages. Some team members learned frontend development from scratch.

### What's next

Our future plans include adding support for video generation on TikTok and YouTube, conducting more customer interviews to learn about their problems and needs, and acquiring early adopters.

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- JavaScript (language) — claimed on Devpost, not found in the code
- Next.js (technology) — claimed on Devpost, not found in the code
- OpenAI (technology) — claimed on Devpost, not found in the code
- Vercel (technology) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.