Library/gpt-crawler
Library/gpt-crawlerForked

BuilderIO/gpt-crawler

gpt-crawler

Crawl a site to generate knowledge files to create your own custom GPT from a URL

Builder

BuilderIO

BuilderIO

BuilderIO • individual

Stars

22,222

Using upstream star count

Forks

2,385

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Nov 14, 2023

Project creation date

README Summary

GPT-Crawler is a TypeScript tool that crawls websites to generate knowledge files for creating custom GPTs. It extracts content from web pages and converts it into a format suitable for training or feeding into GPT models. The tool allows users to build domain-specific knowledge bases from any website content.

AI Dev Skills

Unmapped

Web ScrapingData PreprocessingCustom GPT DevelopmentKnowledge Base CreationText Extraction and ProcessingData Pipeline Engineering

Tags

Web ScrapingData PreprocessingCustom GPT DevelopmentKnowledge Base CreationText Extraction and ProcessingData Pipeline EngineeringLocal DevelopmentDocumentation Processing for AI ModelsContent ManagementSelf-hostedTextEdTechCLI ToolDeveloper ToolsCustom GPT Training Data GenerationDomain-Specific AIKnowledge AugmentationContent Extraction for AI TrainingHTMLDomain-Specific Chatbot DevelopmentAI Training Data CreationWebsite Knowledge Base CreationKnowledge ManagementTypeScriptCLI

Taxonomy

Recent Activity

Updated 9 months ago

7 Days

0

30 Days

0

90 Days

0

Quality

prototype
Quality
medium
Maturity
prototype

Categories

MLOps & InfrastructurePrimaryDev Tools & AutomationML Platform & InfrastructureEdge & Mobile AISearch & KnowledgeOther AI / MLFoundation ModelsModel Training

PM Skills

Scale & ReliabilityDeveloper Platform

Languages

TypeScript100.0%

Timeline

Project created
Nov 14, 2023
Forked
Mar 23, 2026
Your last push
9 months ago
Upstream last push
9 months ago
Tracked since
Jul 7, 2025

Similar Repos

pgvector cosine similarity · $0

Loading…