Skip to content

kiknaio/X-Service-Idea-Scanner

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

X Service Idea Scanner

Scans X (Twitter) for micro-SaaS product opportunities that indie hackers would actually build.

People constantly complain about existing services and products on X. This agent listens, finds patterns, and surfaces actionable ideas backed by real evidence.

How it works

  1. Sends 9 specific search queries to X via Grok (through OpenRouter)
  2. Filters results through an indie hacker lens — would Pieter Levels or Marc Lou build this?
  3. Returns 10 ranked ideas with real evidence, scores, revenue models, and target audiences

Search queries used

  • "someone should build" — direct build requests
  • "I'd pay for" — willingness to pay
  • "why is there no" — market gaps
  • "so frustrating" OR "so annoying" — pain points
  • "I built a" micro saas — what's already working
  • "shut up and take my money" — viral demand
  • "wish there was" — unmet needs
  • "#buildinpublic" pain OR problem — builder struggles
  • "hacked together" OR "duct tape" — workaround signals

What gets filtered out

  • Ideas requiring regulatory compliance, crypto, or hardware
  • Two-sided marketplaces, enterprise sales, geographic lock-in
  • Saturated categories (AI code assistants, todo apps, note apps, generic dashboards)
  • Anything a solo dev can't prototype in an afternoon with Next.js, a database, and Stripe

Setup

# Clone
git clone https://github.com/user/x-service-idea-scanner.git
cd x-service-idea-scanner

# Install
bun install

# Configure
cp .env.example .env
# Add your OpenRouter API key to .env

Get an API key at openrouter.ai. The scanner uses x-ai/grok-4.1-fast which has native X search access.

Usage

Run a scan

bun run scan

Results are saved to results/results-YYYY-MM-DD_HH-mm-ss.json.

Web UI

bun run dev
# Open http://localhost:3000

Browse scans, view ranked ideas, expand details to see evidence, scores, revenue models, and suggested tech stacks.

Output per idea

Field Description
title Specific product name
problem Pain point in the user's language
evidence Real X posts with author, text, URL, engagement
revenue_model freemium, one-time, subscription, usage-based, or marketplace-cut
target_audience Specific niche (e.g. "freelance designers using Figma")
overall_score 1-10 weighted score
suggested_approach Tech stack and distribution channel

Tech stack

  • Runtime: Bun
  • AI: Grok via OpenRouter
  • Frontend: Single HTML file, no dependencies
  • Storage: JSON files on disk

License

MIT

About

Scans X (Twitter) for micro-SaaS product opportunities using Grok. Finds real pain points, validates demand from actual posts, and surfaces ideas an indie hacker can build in a week.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors