Show HN: Agent OS – Safety-first platform for building AI agents with VS Code

    I built Agent OS because I was tired of the "orchestration tax" – writing the same safety checks, memory management, and tool-handling code in every AI agent project.

    What it does:
    - Visual policy editor in VS Code (no more YAML wrestling)
    - Multi-model verification (GPT-4 + Claude + Gemini consensus before risky actions)
    - Built-in compliance frameworks (GDPR, HIPAA, SOC2, PCI-DSS)
    - 50+ agent templates for common use cases
    - One-click deployment to GitHub Actions

    The core idea: Instead of building orchestration on top of your code, Agent OS provides an "operating system" layer that manages permissions, file access, and self-correction.

    Example: Instead of manually checking if your agent's SQL query is safe, you define a policy once and Agent OS enforces it everywhere.

    VS Code Extension: https://marketplace.visualstudio.com/items?itemName=agent-os.agent-os-vscode

    Docs: https://imran-siddique.github.io/agent-os-docs/

    Would love feedback on the approach, especially from anyone dealing with AI safety in production.

Show HN: Agent OS – Safety-first platform for building AI agents with VS Code
github.com