"I built an open source AI agent governance kernel in 3 days as a non-coder"

"Just posted AgentGuard on Hacker News 🛡️
AI agent governance kernel — built in 3 days

Would mean a lot if you checked it out 🙏

You're building with AI agents. Your agent has access to your database, your payments, your users.

What happens when it does something it shouldn't?

Most startups have no answer. No pause button. No audit trail. No trust scoring. No approval gate. Just an agent with full access and a prayer.

AgentGuard changes that.

Mangomindai / agentguard

AI Agent Governance Kernel — trust, approvals, audit

AgentGuard

Constitutional Governance Kernel for AI Agents

"Your AI agents are only as safe as the system governing them." "If your agent can break AgentGuard, it better be good at breaking Bitcoin."

---

Install

pip install agentguard-kernel

The Problem

You're building with AI agents. Your agent has access to your database, your payments, your users.

What happens when it does something it shouldn't?

Most teams have no answer. No pause button. No audit trail. No trust scoring. No approval gate. Just an agent with full access and a prayer.

AgentGuard changes that.

---

Quick Start

from agentguard import TrustEngine
engine = TrustEngine(db_path="trust.db")

# New agent starts TRUSTED
level = engine.get_trust_level("my-agent-001")
print(level)  # → TRUSTED

# Quick permission check
if engine.is_allowed("my-agent-001"):
    # proceed with action
    pass

# Agent does something bad
result = engine.

…

View on GitHub