This problem+solution, like many others in the agentic-space, have nothing agent-specific. Giving a "box" API keys was always considered a risk, and auth-proxying has existed as a solution forever. See tokenizer[0] by the fly.io team, which makes it a stateless service for eg - no database or dashboard. Or the buzzfeed SSO proxy, which lets you do the same via an OAuth2-dance at the frontend, and a upstream config at the backend which injects secrets: https://github.com/buzzfeed/sso/blob/549155a64d6c5f8916ed909....
It's not the same. The core overlap is that agents shouldn't be holding raw credentials, that part isn't new, agreed. But the problem space goes further when you're building for agents specifically:
- Requiring human approval before sensitive actions go through (as @guyb3 mentioned in the post)
- Managing short-lived JWT tokens (refresh/access) with tight TTLs.
- Scoping permissions per-session rather than per-service
Auth-proxying solves the "don't give the box your API key" part. But the approval layer and token lifecycle management are what make this agent-specific, not just "SSO proxy repackaged."
I think you have a point. The credential part feels like a solved problem — auth-proxying has been around for a while. What seems genuinely new to me is the approval layer, the idea that a human should confirm before a sensitive action actually executes. I'm not sure that's covered by tokenizer or SSO proxy, but I could be wrong. Is that the real differentiator here, or am I missing something?
I picked up lobsters last month, and I started to appreciate it much more because of the lack of generated comments. It has a anti-LLM slant, and they have their own moderation challenge (everything is getting tagged as vibecoding - which makes the tag lose meaning). But the comments are noticeable not-slop.
HHVM was not a contribution to PHP. It resulted in PHP 7 being sped up and releasing with a bunch of long awaited features. But afaik , very little of HHVM made it back to PHP core.
pjax is actually listed as an inspiration in the README. It's a great project, but it hasn't been maintained since 2018 and requires jQuery. µJS is dependency-free and covers a much broader feature set.
There is nothing in the dataset that would require the use of a globe to visualize anything. You could have drawn this as bar charts and it would give us the same information (with the added advantage of not being limited to a few countries at a time). Or even a 2D earth map.
It just turns on my CPU fans and gives me no insights.
I've flagged this because this is vibe-coded nonsense that hasn't been tested. It is hosted on Vercel, and Vercel forwards the public IP to the app, which then decides it is a MITM.
[0]: https://github.com/superfly/tokenizer
reply