cdransf/ai.robots.txt
1
1
Fork 0
mirror of https://github.com/ai-robots-txt/ai.robots.txt.git synced 2025-04-03 19:03:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Add Crawlspace

Browse source
This commit is contained in:
Joshua Sheard 2025-01-19 22:03:50 +00:00 committed by GitHub
parent b7f908e305
commit 5aa08bc002
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 8 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
robots.json
View file

@ -90,6 +90,13 @@
"frequency": "Unclear at this time.",
"description": "cohere-training-data-crawler is a web crawler operated by Cohere to download training data for its LLMs (Large Language Models) that power its enterprise AI products. More info can be found at https://darkvisitors.com/agents/agents/cohere-training-data-crawler"
},
"Crawlspace": {
"operator": "[Crawlspace](https://crawlspace.dev)",
"respect": "[Yes](https://news.ycombinator.com/item?id=42756654)",
"function": "Scrapes data",
"frequency": "Unclear at this time.",
"description": "Provides crawling services for any purpose, but most likely to be used for AI model training."
},
"Diffbot": {
"operator": "[Diffbot](https://www.diffbot.com/)",
"respect": "At the discretion of Diffbot users.",
@ -300,4 +307,4 @@
"frequency": "No information.",
"description": "Retrieves data used for You.com web search engine and LLMs."
}
}
}