HackerTrans
TopNewTrendsCommentsPastAskShowJobs

LunarFrost88

no profile record

Submissions

Show HN: Railguard – A safer –dangerously-skip-permissions for Claude Code

github.com
1 points·by LunarFrost88·4 tháng trước·3 comments

Show HN: Railyard – open and secure runtime for Claude Code

3 points·by LunarFrost88·4 tháng trước·5 comments

Show HN: I built a tool to help teams automate basic analytical tasks

3 points·by LunarFrost88·6 tháng trước·0 comments

Show HN: I built a tool to help small teams automate basic analytical tasks

2 points·by LunarFrost88·7 tháng trước·7 comments

Eng stack for a typical 2-person startup today

1 points·by LunarFrost88·7 tháng trước·2 comments

Show HN: An agent that analyzes both structured and unstructured data in minutes

1 points·by LunarFrost88·7 tháng trước·0 comments

comments

LunarFrost88
·4 tháng trước·discuss
Railguard is really meant for preventing CC from running unsafe commands, and be really good at that. There probably needs to be a separate reviewer / LLM-as-a-judge to catch behavioral issues.

It’s rule based. We don’t use LLM-based checks precisely because of what you said.
LunarFrost88
·4 tháng trước·discuss
I'm the author, AMA!
LunarFrost88
·4 tháng trước·discuss
We've built something similar, but in Rust.

https://github.com/railyard-dev/railguard
LunarFrost88
·4 tháng trước·discuss
Just added the ability to track all the commands monitored+blocked by Railyard. We hope you give it a try!

Type:

railyard dashboard
LunarFrost88
·4 tháng trước·discuss
Thanks! We are trying to be complementary and focused on hardening Claude Code to production-grade guarantees. I think this can only be done properly with OSS, because teams will need to adjust the guardrails to make the runtime uniquely theirs.
LunarFrost88
·4 tháng trước·discuss
Thanks for the feedback. Love the point about the visualization dashboard, will add that now!

>> have you tried integrating this with multi-agent setups, where multiple Claude Code instances interact?

We wanted to solve for the most frequent use case first (single-agent execution), but multi-agent is definitely on the cards. If you've got some use cases in mind, let me know and we'll apply Railyard to it.
LunarFrost88
·7 tháng trước·discuss
Fixed!
LunarFrost88
·7 tháng trước·discuss
Appreciate you pasting it explicitly!

Verdict?
LunarFrost88
·7 tháng trước·discuss
That's good feedback. Honestly, it's so early (we are working with design partners) that we haven't really thought about pricing for orgs and enterprises yet. So we left it as 'Talk to Us'.

Agree that an individual analyst should get all those features, and the team tier should be more about sharing and admin controls.