cdransf/ai.robots.txt
1
1
Fork 0
mirror of https://github.com/ai-robots-txt/ai.robots.txt.git synced 2025-04-04 19:13:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge pull request #71 from jsheard/patch-1

Browse source 
Add Crawlspace
This commit is contained in:
Glyn Normington 2025-01-20 17:45:29 +00:00 committed by GitHub
commit f621fb4852
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

7
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, probably including AI model training."
},
"Diffbot": {
"operator": "[Diffbot](https://www.diffbot.com/)",
"respect": "At the discretion of Diffbot users.",