I guess I don't understand how Openclaw and agent are workin...

npub1eaadqhuwn80gatdml02u58q0nd65nx7wqur5je4jwa5gef0p6unqrx54mw
hex
68d1c72fcc09aeac1b4b473dff91bcc1bdfc1c3324b25b3034ceb145ddcb1b45nevent
nevent1qqsx35w89lxqnt4vrd95w00ljx7vr00ursejfvjmxq6vav29mh93k3gprpmhxue69uhhyetvv9ujuem4d36kwatvw5hx6mm9qgsv77kst78fnh5w4kalh4w2rs8eka2fn08qwp6fv6e8w6yv5hsawfsssrfq6Kind-1 (TextNote)
↳ 回复 事件不存在
1a532dcb44c3fa18aebae1af97763822b30a9a0832805dc0f94b830c2cee5aff...
I guess I don't understand how Openclaw and agent are working. I thought if I asked to do a program that check an API every hours, then the program run without agent to ask anything to the model, so. But I guess it's not the case. I know for NWC but I don't like the idea that it draw sats without my approval, so if something strange is happening like 5 bucks got killed in minutes, I can stop and figure out. But I guess with proper limits it might be acceptable once I trust the tool to not go crazy.
Then I cannot imagine when I will deploy all thr automation I planned for, checking message, emails, calendars and a lot more. I would better ask it to program n8n to run outside the agent or something.
原始 JSON
{
"kind": 1,
"id": "68d1c72fcc09aeac1b4b473dff91bcc1bdfc1c3324b25b3034ceb145ddcb1b45",
"pubkey": "cf7ad05f8e99de8eadbbfbd5ca1c0f9b75499bce07074966b277688ca5e1d726",
"created_at": 1772800537,
"tags": [
[
"alt",
"A short note: I guess I don't understand how Openclaw and agent ..."
],
[
"e",
"2dac88d66c241acdfb23f9869bd56c9be4b62976337b3a2568305a9cf556ce1c",
"wss://relay.damus.io/",
"root",
"9dd283b1bdcea8cab10a8bca1d1677f7117d3e87090a1bd401cfb21fcf9b6beb"
],
[
"e",
"cbc9c6e96dc70afe49a8d188682886f12aa25052d6394795885b758cf4ebe58c",
"wss://nos.lol/",
"",
"d22bcdb1d2505bc060f65a86cd5f20532ec5f3e41c06aea9edac39f6ba76fd6e"
],
[
"e",
"1a532dcb44c3fa18aebae1af97763822b30a9a0832805dc0f94b830c2cee5aff",
"wss://nos.lol/",
"reply",
"d22bcdb1d2505bc060f65a86cd5f20532ec5f3e41c06aea9edac39f6ba76fd6e"
],
[
"p",
"cf7ad05f8e99de8eadbbfbd5ca1c0f9b75499bce07074966b277688ca5e1d726",
"wss://relay.nostr.band/"
],
[
"p",
"cf7ad05f8e99de8eadbbfbd5ca1c0f9b75499bce07074966b277688ca5e1d726",
"wss://relay.nostr.band/"
],
[
"p",
"d22bcdb1d2505bc060f65a86cd5f20532ec5f3e41c06aea9edac39f6ba76fd6e",
"wss://nos.lol/"
],
[
"p",
"9dd283b1bdcea8cab10a8bca1d1677f7117d3e87090a1bd401cfb21fcf9b6beb",
"wss://21ideas.nostr1.com/"
]
],
"content": "I guess I don't understand how Openclaw and agent are working. I thought if I asked to do a program that check an API every hours, then the program run without agent to ask anything to the model, so. But I guess it's not the case.\nI know for NWC but I don't like the idea that it draw sats without my approval, so if something strange is happening like 5 bucks got killed in minutes, I can stop and figure out. But I guess with proper limits it might be acceptable once I trust the tool to not go crazy. \n\nThen I cannot imagine when I will deploy all thr automation I planned for, checking message, emails, calendars and a lot more. I would better ask it to program n8n to run outside the agent or something. ",
"sig": "438cc26f4c401d2ecf60205a1d8e2bf8fbbcfdf906763751859e9bd991ce8d614b76c03e5391d5fe554a3303de29d6397c1eaa5710ad3fded1372e6081eb7d42"
}