Pricing

$1.00 / 1,000 results

Docs Change Monitor for AI

Monitor public docs, changelogs, help centers, status pages, and pricing pages for changes, then output clean Markdown and RAG-ready chunks for AI knowledge bases.

Pricing

$1.00 / 1,000 results

Rating

0.0

(0)

Developer

Carey Brown

Actor stats

Bookmarked

Total users

Monthly active users

24 days ago

Last modified

Categories

Developer tools

Automation

Start URLs

startUrls

Required

Public pages to monitor. MVP local validation requires matching fixturePages entries and does not fetch the network.

Type:object[]

Default:

[
  {
    "url": "https://example.com/docs/overview",
    "label": "Example Docs",
    "pageType": "docs"
  }
]

Fixture Pages

fixturePages

Optional

Local MVP fixture HTML keyed by URL. This exists for offline validation only; live fetching remains approval-gated.

Type:object

Default:

{}

Previous Snapshots

previousSnapshots

Optional

Optional prior snapshot state keyed by URL for local diff validation.

Type:object

Default:

{}

Chunk Size

chunkSizeChars

Optional

Approximate character size for RAG chunks.

Type:integer

Minimum:500

Maximum:5000

Default:1800

Chunk Overlap

chunkOverlapChars

Optional

Character overlap between adjacent chunks.

Type:integer

Minimum:0

Maximum:1000

Default:200

Change Threshold Ratio

changeThresholdRatio

Optional

Minimum approximate text-change ratio for changed events.

Type:number

Minimum:0

Maximum:1

Default:0.02

Emit Unchanged Pages

emitUnchangedPages

Optional

Include unchanged page events in output.

Type:boolean

Default:false

Emit Baseline Pages

emitBaselinePages

Optional

Include first-run baseline records in output.

Type:boolean

Default:true

Respect Robots.txt

respectRobotsTxt

Optional

Recorded in output source metadata. MVP does not fetch robots.txt.

Type:boolean

Default:true

Maximum Pages

maxPages

Optional

Maximum pages to process from startUrls in this local MVP.

Type:integer

Minimum:1

Maximum:500

Default:25

Network Mode

networkMode

Optional

MVP supports fixture-only validation. Live network fetching requires a later approval packet.

Type:string

Default:fixtures_only

Options:

fixtures_onlylive_fetch

Maximum HTTP Requests

maxRequests

Optional

Maximum HTTP requests for approved local live_fetch validation. Includes robots.txt checks.

Type:integer

Minimum:1

Maximum:12

Default:12

Request Delay

requestDelayMs

Optional

Delay between live_fetch HTTP requests in milliseconds.

Type:integer

Minimum:0

Maximum:10000

Default:1000

Request Timeout

requestTimeoutSecs

Optional

Timeout for each live_fetch HTTP request in seconds.

Type:integer

Minimum:1

Maximum:60

Default:20

Website Content Extractor for RAG: Markdown, HTML, Text

nezha/website-content-crawler

Turn docs sites, help centers, blogs, and websites into clean markdown, text, or HTML for RAG, AI knowledge bases, and internal search. Crawl from start URLs or sitemaps and keep the crawl in scope.

nezha

5.0

Docs & Help Center to RAG JSONL

orbiscribe/docs-help-center-rag-snapshot

Paste a docs or help center URL and get clean Markdown, breadcrumbs, page records, and JSONL chunks for RAG.

Orbiscribe Labs

Website Content Scraper

qaseemiqbal/website-content-scraper

Extract clean Markdown, plain text, linked files, and RAG-ready chunks from websites, documentation, help centers, knowledge bases, and authenticated portals. Preserve structure, metadata, URLs, and crawl context for AI search, training, and retrieval workflows.

Muhammad Qaseem Iqbal

Website Changelog & Pricing Change Tracker

happyfhantum/changelog-buying-trigger-miner

Monitor pricing pages, changelogs, and product pages for buying-trigger changes.

Kelsey Todd

Docs-to-RAG AI Crawler

charitable_jeopardy/WebScraperAp

Stop wasting space on website headers, footers, cookie banners, and navigation menus. Extract clean body text, chunk it for RAG, and detect page changes across runs crawling public docs, blogs, and knowledge bases,

charitable_jeopardy

Website to RAG Markdown Crawler

knotted_tussock/rag-markdown-crawler

Crawl any website or docs site and export clean Markdown plus JSONL-style chunks for RAG, LLM apps, and AI agents.

Ralph T

Docs Markdown Rag Ready Crawler

devwithbobby/docs-markdown-rag-ready-crawler

Turn any documentation site or website into clean, structured markdown—ready for RAG, embeddings, and AI agents.

Dev with Bobby

Website Content Extractor

taroyamada/website-content-extractor

Extract clean text and markdown from docs, pricing, product, policy, and help-center URLs for RAG datasets and content operations.

naoki anzai

AI Web Content Crawler - Markdown for LLMs

intelscrape/ai-web-content-crawler

Crawl any website and extract clean Markdown optimized for LLM training, RAG pipelines, and AI knowledge bases - removes boilerplate and outputs structured JSON with URL, title, markdown, and metadata.