It’s rule based. We don’t use LLM-based checks precisely because of what you said.
https://github.com/railyard-dev/railguard
--dangerously-skip-permissions is all-or-nothing. Either you approve every tool call by hand, or Claude runs with zero restrictions. I wanted a middle ground.Railguard hooks into Claude Code and intercepts every tool call and decides in under 2ms: allow, block, or ask. cargo install railguard ...
Type:
railyard dashboard
>> 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.
We're a small startup (but have ~15 years of experience building software), so we try to run Claude Code as autonomously as possible. The goal is to spend most of our time talking to customers instead of babysitting the agent. But --dangerously-skip-permissions felt a bit too wild west for us.So we built a runtime to make autonomous use safer. Railyard is an open-source runtime that sits...
Arka is a AI analytics tool that lets you get insights + charts from any (structured or unstructured) data source. I built it because I was getting tired of writing SQL queries and creating Metabase charts at my last job.I would love some feedback on our product:1. How is the landing page / website2. What use cases could this unlock for you?We have some awesome tech behind the scenes and have...
Verdict?
Agree that an individual analyst should get all those features, and the team tier should be more about sharing and admin controls.
Arka (arka.so) is a AI analytics tool that lets you get insights + charts from any (structured or unstructured) data source. I built it because I was getting tired of writing SQL queries and creating Metabase charts at my last job.I would love some feedback on our product:How is the landing page / websiteWhat use cases could this unlock for you?We have some awesome tech behind the scenes and...
We're building arka.so. We are a 2-person team, and my mind is blown. You can achieve things I couldn’t have imagined a few years ago.I think we’ve essentially unlocked unlimited engineering capacity for routine tasks, thanks to these AI tools.First, we built everything serverless and chose Vercel. The bigger cloud vendors are great, but unless you have hundreds of customers, they’re often...
I’ve been building a small AI agent that can analyze both structured and unstructured data in minutes, things like CSVs, product logs, support tickets, CRM notes, PRs, etc.The motivation is personal: at every company I’ve worked at, our data was scattered across warehouses, Slack, GitHub, Asana, and a dozen other tools. I spent way too much time copy-pasting from one source to another just to...
Hey HN,I'm Ari, I previously led AI at Asana and built databases at AWS.We built Arka for startups who need insights from their data but don’t have the time (or team) to build out a full analytics stack.Does this sound like you?1. Your investors, customers, product, marketing, and ops are all asking for answers 2. Your data lives across Postgres, Stripe, Segment, maybe Databricks, even Slack 3....
Hi HN,I’m excited to introduce Mode, now in early access! Mode is a Visual Studio Code extension I’ve been working on, acting as your personal AI code copilot. It’s a reliable backup to coding tools like Cursor, especially when you run out of free tokens.Try it out here: https://marketplace.visualstudio.com/items?itemName=aruna-la...Why Use Mode:Bypass Token Limitations: If you find yourself...