# BuilderIO/gpt-crawler

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

Repository: https://github.com/BuilderIO/gpt-crawler
Canonical: https://ross.abutalabs.com/products/gpt-crawler
Homepage: https://www.builder.io/blog/custom-gpt
Language: TypeScript
License: ISC
License Family: permissive
Topics: ai
Last push: 2025-07-07T15:35:16+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 30, release rhythm 8, longevity 73
- inputs: {"age_days": 1024, "days_push": 422, "days_rel": 588, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 22393, forks 2368 (observed 2026-08-28T04:11:32.587348+00:00)

## What it is
A Node.js/TypeScript crawler that scrapes one or more websites and generates knowledge files (JSON) for creating custom GPTs or OpenAI assistants. It can run locally, in Docker, or as an API.

## Use cases
- create a custom GPT from a documentation site
- crawl a website to generate knowledge files for OpenAI assistants
- turn any site into a chatbot knowledge base
- scrape docs into JSON for RAG ingestion
- build a support bot from my website content

## When to choose
- you want to build a custom GPT or assistant grounded in a specific site's content
- you need a quick, configurable site crawler that outputs structured JSON

## When to avoid
- you need a full RAG pipeline with embeddings and vector storage
- you need large-scale, distributed crawling with scheduling

## Facets
- artifact type: cli-tool
- maturity: active
- function: web-scraping, rag, data-generation, cli
- domain: artificial-intelligence, large-language-models, crawlers, developer-tools
- platform: cli, cross-platform
- tags: custom-gpt, openai, knowledge-files, crawler, playwright, nodejs, docker

## Member repositories
- BuilderIO/gpt-crawler (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:32.587348+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:57:11.051646+00:00, confidence not recorded.
  - readme: https://github.com/BuilderIO/gpt-crawler (fetched 2026-08-28T04:11:32.587348+00:00, sha 0a5648a230f6)
  - homepage: https://www.builder.io/blog/custom-gpt (fetched 2026-08-29T07:55:57.563670+00:00, sha e3d75f06d401)
  - site_page: https://www.builder.io/c/docs/developers (fetched 2026-08-29T07:55:57.569307+00:00, sha 10bb2aa68f1d)
  - site_page: https://www.builder.io/m/about-us (fetched 2026-08-29T07:55:57.574959+00:00, sha 686c281d03b7)
  - site_page: https://www.builder.io/c/docs/get-started-fusion (fetched 2026-08-29T07:55:57.577285+00:00, sha e2133b056fc4)
  - site_page: https://www.builder.io/c/docs/get-started-publish (fetched 2026-08-29T07:55:57.583711+00:00, sha 736c3720b918)
  - site_page: https://www.builder.io/pricing (fetched 2026-08-29T07:55:57.566794+00:00, sha 0fb592ca72d9)
  - site_page: https://www.builder.io/integrations (fetched 2026-08-29T07:55:57.586202+00:00, sha e288e66e5b1e)
- Data as of 2026-08-30T08:39:29.467469+00:00.