More

bsgeraci · 2026-04-01T11:41:51 1775043711

Dang! Glad to see others doing this. I totally made this site yesterday like 11 hours ago :/ but did not get the traction.

I love your implementation.

Here was my first stab:

https://news.ycombinator.com/item?id=47595140

https://brandonrc.github.io/journey-through-claude-code/

kordlessagain · 2026-04-01T14:15:57 1775052957

That's where we are now, lots of us doing similar. Don't get hung up on who gets noticed, that "value" is almost zero now.

bsgeraci · 2026-04-01T00:07:51 1775002071

I had claude code use the src code that was recently leaked to build an interactive website that explores claude code. :)

This was first pass with no modifications. I might have to go back and forth but pretty dang cool if you care about the nitty gritty.

bsgeraci · 2026-02-07T13:15:32 1770470132

Want to thank everyone for taking the time to make comments here. I am using what was said to improve the code base.

Currently active in some refactors. If anyone wants to test ArtifactKeeper I recommend waiting for my 1.0.0.a2 release. Hopefully by the end of the weekend.

Thanks again!!!

bsgeraci · 2026-02-07T01:20:41 1770427241

https://github.com/artifact-keeper

There are 7 or 8 repositories now in this org. Feel free to take, use, or help imrove the code. MIT Open Source.

deknos · 2026-02-08T08:49:58 1770540598

thanks. another question:

Would it be possible, that the storage of pypi/whatever is some s3 bucket, where you have it encrypted (with authentication), and when you deliver it to a client, you get it, decrypt it, test for authentication and deliver it to the client? the encryption is something that artipie is lacking sadly.

bsgeraci · 2026-02-07T01:18:43 1770427123

yea so technically some of the formats are aliased :)

https://artifactkeeper.com/docs/package-formats/ Check this, you should see around 35 then 9 alias's that map to the other ones.

bsgeraci · 2026-02-07T00:45:01 1770425101

That is interesting, I have a good idea about setting up some red team agents and blueteam agents with claude code and seeing if we can improve security by testing things. In the pen test world these AI tools have basically beat all humans breaking into systems with no AI assistance.

If you have anymore details I would love to hear from your experience and what you think would be useful to look at. I will make a ticket based on this concern. I really want to make this as secure as we can and have people poke and do the code reviews. :)

Or analyse the code base. I am using security agents to harden the code base and testing end to end testing based on that.

Adding some security agents in the loop is a great idea!

bsgeraci · 2026-02-06T22:19:17 1770416357

I really think my next step is a full on CLI/TUI :)

Basically I am using end points so automation can be done with just curl requests. But as a linux nerd I do enjoy my share of CLI/TUI's.

bsgeraci · 2026-02-06T19:09:35 1770404975

Thanks for the kind words! If you need any help please reach out. My contact info is on github and I am happy to support making this happen.

bsgeraci · 2026-02-06T19:07:49 1770404869

I think we are in a time where we can make amazing things happen. I always go back to my Star Trek shows. We can now ask a computer to make a program for us. That is what I have been dreaming of. Now we are not at that level and lots of thought and experience goes into helping guide claude code but it is sometimes sci-fi like. The code is more clean, more maintainable for even myself. Everytihng is always commented, complexity is reduced.

I think if you follow a few rules whenever making changes and using all the latest tools like linters, security checkers, end to end frameworks, and any other helpful tool you can really make stuff happen.

bsgeraci · 2026-02-06T19:04:35 1770404675

I am totally thinking about adding this so you can connect to an API or use self hosted models that run in a container if you have the resources!!!! You are spot on.