Show HN: Script to bulk delete Claude chats from the web UI

Posted by ML0037 5 days ago

Counter60Comment21OpenOriginal

I haven't found a way to delete all chats in bulk like you can on Chatgpt. With Claude, you have to scroll to the bottom, select everything, and delete. The problem is, if you have a lot of chats, it becomes impossible. I created this script. It does it alone. I hope it helps someone.

(conversations disappear from the UI slowly, over several minutes, and remember to keep the tab open until the console shows "Finished", refreshing away from the page can stop the deletion process.)

Comments

Comment by crystal_revenge 4 days ago

For pure, weird, late-night LLM chats, I've recently started using Qwen3.6-35B-A3B-Uncensored just running with llama-cli and it is a very refreshing chat experience.

Uncensored model means it will not deny any requests (at least I have yet to come across one), if you grew up in the 90s it sort of feels like coming across the anarchist cookbook for the first time (though with more accurate content). Using llama-cli means the session is entirely local and entirely ephemeral. As a bonus all the reasoning steps are fully visible to the user.

The base Qwen3.6-35B-A3B is more than adequate for "weird late night brainstorming chats" and I've really started to dislike the natural tendency to self-censor when the model is willing to refuse (and potentially report) any requests it feels is "inappropriate" and all these private thoughts are stored on someone else's server.

Comment by Xeoncross 4 days ago

Even for work questions about sensitive IP/code Qwen3.6-35B-A3B is a great option on macOS (35t/s) when you don't want info leaving your laptop. I'm using it with oMLX.

Comment by vorticalbox 4 days ago

I switched to oMLX today from lm studio. Really nice but I have found qwen3.6 sometimes failing to call tools correctly.

Comment by nozzlegear 4 days ago

I use oMLX and also have this issue with qwen. Not sure what it is about oMLX + qwen but they don't seem to play well together.

Comment by bastawhiz 4 days ago

I run a Gemma 4 32b abliteration (int8) and it's remarkably good. It's been a real step up from Qwen in my experience.

Comment by tough 3 days ago

you can even use stuff to uncensor any foss model

Comment by c7b 4 days ago

Wouldn't downloading conversations be more useful? If you've input something into Claude that you don't want a future trillion-dollar US company (a bicorn?) to know, this script won't help I'm afraid. Free reminder that local AI exists and works well if you're willing to tinker a bit.

Comment by miguel-muniz 4 days ago

I have a similar complaint every AI chat product I've used. There's no way to multi-select conversations and delete them in a single action. It's either delete all or click on the delete button and confirm for every single one.

With many leaders in tech claiming that AI agents have drastically reduced the time and cost of shipping features, how do such small usability problems still not get fixed after years?

Comment by cpeterso 4 days ago

The Claude (and ChatGPT) web UI supports incognito/temporary chats that are discarded when you close the tab. Click the ghost or dotted speech bubble icon in the upper right corner of the page.

I use this as my default mode so I don't clutter my chat history with random, one-off questions I ask. Unfortunately, there is no way to change your mind and save a productive incognito chat after you've started chatting.

Comment by Wowfunhappy 4 days ago

I feel like every time I try to use this feature, I get burned because I accidentally use the back touchpad gesture, or I accidentally close the tab, etc. Or, I remember one time I was using the Claude iPhone app, and I quickly switched apps to respond to a text message. My phone must have been low on memory or something, because as soon as I switched back to Claude, the app faded to the startup screen and the whole conversation was gone.

Which of course is the entire point, so I don’t really know what I want here, but what they have right now isn’t that usable IMO. Maybe a chat that lasts 24 hours? And, it would be nice if there was a way to convert an incognito chat into a persistent chat.

Comment by vorticalbox 4 days ago

the request still went to a server you have no control over.

For all we know these temporary chats are saved and linked to your account but just don’t show up in the UI.

Comment by steve_adams_86 4 days ago

I believe they are. In the case of my organization's account, Incognito chats are even visible to admins.

An interesting/odd way to think about the feature is that you're not hiding the chats from other humans, but from Claude.

Comment by unethical_ban 2 days ago

If the privacy policy is to be believed, they save them for 30 days for presumably investigative purposes, but do no keep them longer, permanently associate them to your account or use them for model training.

Comment by ur-whale 5 days ago

Which of course assumes, that the "delete chat" function actually deletes anything from Anthropic's datastore.

Comment by hootz 4 days ago

This can be used for general organization or privacy against other people, not just trying to hide conversations from Anthropic.

Comment by ML0037 5 days ago

Comment by petesergeant 5 days ago

How are you managing it with ChatGPT? I've always found Claude relatively easy to do it with, but unless they've changed it in the last few weeks it's hard with ChatGPT.

Edit: I should add I often want to keep one or two reference chats, so the "nuke all chats" button doesn't work for me.

Comment by ML0037 5 days ago

Hi! for ChatGPT I go in settings -> Data Controls -> delete all chat

Comment by 5 days ago

Comment by RajX-dev 4 days ago

you are a saviour brother

Comment by bulldo_gs 4 days ago

[flagged]

Comment by alfanick 5 days ago

[flagged]

Comment by 542458 5 days ago

It's 100 lines of unobfuscated js. If you're worried just read it.

Comment by 5 days ago

Comment by alfanick 5 days ago

[flagged]

Comment by 3997531578 5 days ago

[dead]

Comment by turkeyboi 5 days ago

Delete account. Make new.