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.
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.
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.
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.
It’s rule based. We don’t use LLM-based checks precisely because of what you said.