arkon-ai/arkon
The AI Operations Control Plane — monitor, govern, and automate your AI agents
Platform-specific configuration:
{
"mcpServers": {
"arkon": {
"command": "npx",
"args": [
"-y",
"arkon"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset=".github/assets/readme-banner-dark.png"> <source media="(prefers-color-scheme: light)" srcset=".github/assets/readme-banner-light.png"> </picture> </p>
<p align="center"> <strong>AI Governance Platform</strong> — Monitor your agents. Detect threats. Track costs. Build workflows. </p>
<p align="center"> <a href="#quick-start">Quick Start</a> · <a href="#features">Features</a> · <a href="https://arkonhq.com">Website</a> · <a href="https://demo.arkonhq.com">Live Demo</a> · <a href="INSTALL.md">Full Install Guide</a> · <a href="API.md">API Docs</a> </p>
<p align="center"> </p>
---
I was running AI agents via OpenClaw — building automations, managing infrastructure, doing real work. And things kept going wrong.
My agent leaked API credentials five times. Not because I forgot to set rules — I made it rule number one, in bold, in the system prompt, in the soul file, everywhere I could put it. Didn't matter. Passwords, API keys, tokens — they kept showing up in chat logs and channel messages. I had an agent with access to a database containing thousands of people's personal records and payment details. One leaked credential and all of that is exposed.
Then my agent burned through $20 of API credits in thirty minutes using a model I explicitly told her not to use. I had no alert, no spending cap, no visibility — I found out after the money was gone. Another time, she started modifying config files I told her not to touch. I told her to stop. She didn't stop. She broke the environment. I spent two hours fix
Loading reviews...