Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Viewing profile — saranshrana

saranshrana

HN member
Joined
Mon, Feb 09, 2026, 4:09 PM UTC
HN karma
3
Public activity
6 items

About saranshrana

Building Runtime Security platform for AI Agents and Co-Pilots

try it out - https://burrow.run

Recent public activity

  1. story
    Show HN: Burrow – Runtime Security for AI Agents

    We use Claude Code, Cursor, and Copilot daily. These tools run shell commands, read files, and call APIs on their own. When something goes wrong you find out after. A .env file get…

  2. comment
    Comment #47749936

    Honestly, best solution is to use native CSP solutions like AWS Secrets Manager, AWS SSM Parameter Store, GCP Secret Manager, Terraform Vault. All these have native audit logs and …

  3. comment
  4. story
    Ask HN: How are you handling runtime security for your AI agents?

    Our team uses Claude Code, OpenClaw, Claude CoWork and Cursor daily. These tools run shell commands, read files, and call APIs autonomously. We have zero visibility into what happe…

  5. comment
    Comment #47748656

    Runtime Security for AI Agents and Co-Pilots Try it here - https://burrow.run/

  6. comment
    Comment #47714123

    Interesting work, just curious, are you defining Agent Identity at the MCP layer itself ? assuming "SessionID" -> Agent Identity (Randomised) ?