gitwtfhub

wtf is ad-research-agent?

igm61799-cloud/ad-research-agent — explained in plain English

Analysis updated 2026-05-18

18JavaScriptAudience · pm founderComplexity · 2/5Setup · easy

TL;DR

A tool that scrapes your site and competitor sites to build a swipe file of proven ad hooks and offers you can paste into Claude.

Mindmap

mindmap
  root((ad-research-agent))
    What it does
      Scrapes brand and competitor sites
      Extracts proven hooks
      Builds a swipe file
    Tech stack
      Node.js
      JavaScript
      Anthropic API
    Use cases
      Write new ad scripts
      Research competitor offers
      Pull live running ads
    Audience
      Marketers
      Founders
      Copywriters

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Build a swipe file of proven ad hooks and offers from your own site and competitors.

REASON 2

Feed real ad patterns into Claude to write new ad scripts instead of starting from a blank page.

REASON 3

Pull live running Meta and TikTok ads for your niche using an optional PipiAds key.

REASON 4

Research competitor pricing and offer structures automatically.

What's in the stack?

Node.jsJavaScript

How it stacks up

igm61799-cloud/ad-research-agentbluejacketblackhawk/saysomethingchinaran0/wujing_dic
Stars181818
LanguageJavaScriptJavaScriptJavaScript
Setup difficultyeasymoderateeasy
Complexity2/53/52/5
Audiencepm foundergeneralops devops

Figures from each repo's GitHub metadata at analysis time.

How do you spin it up?

Difficulty · easy Time to first run · 30min

Needs your own Anthropic or OpenAI API key, a PipiAds key is optional for live ad data.

Wtf does this do

Ad research agent is a tool that scrapes your own brand's website and any competitor sites you point it at, then pulls out the marketing patterns that already seem to work: proven hooks, selling angles, offer and pricing structures, call to action phrases, and any testimonials. It bundles everything it finds into a single markdown file, a swipe file, that you can paste straight into a Claude chat so whoever writes the actual ad script starts from real examples instead of a blank page. An earlier version of this project tried to generate video ads directly, but that step was slow and the results were weak, so it was removed. The project now focuses only on research: finding what already works rather than writing the ad itself. It runs entirely on your own computer using your own API keys, with no login and no shared servers. You need Node.js 18 or newer and an Anthropic or OpenAI API key. On Windows you can run it without touching a terminal: double click one file to set it up, add your API key to a text file, then double click another file to open a browser based form where you enter your brand and competitor sites and click a button to start the research. There is also a plain command line path for people who prefer that. The tool works through five steps: it builds a list of sites to check, your brand, any competitors you name, and optionally more competitors it guesses and then verifies by actually visiting them, scrapes each site's most relevant pages such as pricing and product pages, extracts the patterns mentioned above from each one, optionally pulls live running ads from Meta and TikTok if you provide a PipiAds API key, and finally writes everything into the swipe file along with a ready made prompt block to paste into Claude. Competitor discovery relies on the AI's own knowledge rather than a live search, so it can miss brand new competitors or guess a wrong web address, giving it explicit competitor URLs is more reliable. Costs are billed directly to your own Anthropic account and are typically a few cents per run.

Yoink these prompts

Prompt 1
Walk me through setting up ad-research-agent on Windows without using a terminal.
Prompt 2
Show me how to configure research.config.json with my brand and competitor URLs.
Prompt 3
Use the swipe-file.md output from ad-research-agent to write three new ad hooks for my brand.
Prompt 4
Explain how ad-research-agent's competitor discovery step verifies guessed competitor URLs.

Frequently asked questions

wtf is ad-research-agent?

A tool that scrapes your site and competitor sites to build a swipe file of proven ad hooks and offers you can paste into Claude.

What language is ad-research-agent written in?

Mainly JavaScript. The stack also includes Node.js, JavaScript.

How hard is ad-research-agent to set up?

Setup difficulty is rated easy, with roughly 30min to a first successful run.

Who is ad-research-agent for?

Mainly pm founder.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.