mirror of
https://github.com/ai-robots-txt/ai.robots.txt.git
synced 2025-06-19 02:00:51 +00:00
Merge pull request #143 from ai-robots-txt/panscient
chore(robots.json): adds Panscient
This commit is contained in:
commit
2fca1ddcf1
1 changed files with 14 additions and 0 deletions
14
robots.json
14
robots.json
|
@ -342,6 +342,20 @@
|
|||
"frequency": "Unclear at this time.",
|
||||
"description": "PanguBot is a web crawler operated by the Chinese company Huawei. It's used to download training data for its multimodal LLM (Large Language Model) called PanGu. More info can be found at https://darkvisitors.com/agents/agents/pangubot"
|
||||
},
|
||||
"Panscient": {
|
||||
"operator": "[Panscient](https://panscient.com)",
|
||||
"respect": "[Yes](https://panscient.com/faq.htm)",
|
||||
"function": "Data collection and analysis using machine learning and AI.",
|
||||
"frequency": "The Panscient web crawler will request a page at most once every second from the same domain name or the same IP address.",
|
||||
"description": "Compiles data on businesses and business professionals that is structured using AI and machine learning."
|
||||
},
|
||||
"panscient.com": {
|
||||
"operator": "[Panscient](https://panscient.com)",
|
||||
"respect": "[Yes](https://panscient.com/faq.htm)",
|
||||
"function": "Data collection and analysis using machine learning and AI.",
|
||||
"frequency": "The Panscient web crawler will request a page at most once every second from the same domain name or the same IP address.",
|
||||
"description": "Compiles data on businesses and business professionals that is structured using AI and machine learning."
|
||||
},
|
||||
"Perplexity-User": {
|
||||
"operator": "[Perplexity](https://www.perplexity.ai/)",
|
||||
"respect": "[No](https://docs.perplexity.ai/guides/bots)",
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue