RAG Dataset Linter
Audit RAG chunks for duplicates, broken ordering, excessive overlap, missing provenance, and malformed content before vector database ingestion.
17%
users
Apify builder
Sebastián S I build focused web-data tools for SEO, content, and automation workflows.
Leaderboard position
out of 10,354
New actors
-
Total actors
#2,442
↓ -798
Monthly users
#2,951
↓ -852
Total users
#3,856
↓ -717
Monthly runs
#2,731
↓ -1,050
Total runs
#2,341
↓ -259
Portfolio stats
New actors
0
+0
Total actors
6
+0
Monthly users
6
+0
Total users
16
+0
Monthly runs
170
↓ -92
Total runs
1,399
↑ +168
New actors
Each bar shows one day in the last 30 days.
Portfolio concentration
5 of 6 actors cover 80%+ of monthly users.
Audit RAG chunks for duplicates, broken ordering, excessive overlap, missing provenance, and malformed content before vector database ingestion.
17%
users
Audit sitemap lastmod, schema dates, and page freshness with static HTTP checks and deterministic issue codes.
17%
users
Check robots.txt, sitemaps, static extraction quality, crawl risk, and estimated Apify costs before running a crawler or RAG ingestion job.
17%
users
Convert public websites, docs, blogs, and XML sitemaps into clean Markdown, structured metadata, and stable chunks for RAG pipelines and vector databases.
17%
users
Extract public YouTube comments and replies with text, likes, authors, badges, pinned and hearted signals, and creator interactions. No YouTube API key or login is required.
17%
users
ActorHunt MCP
ActorHunt gives paid members MCP access to keyword data, actor evidence, and Store movement for deciding what to build next.