top of page

We Published a Governance CLI for Multi-Agent AI

Mar 13
1 min read

We just published palyan-cli to npm. It is the first governance-first command line tool for multi-agent AI systems.

Most CLI tools in the AI space help you write code faster. This one helps you govern what your agents actually do.

palyan-cli wraps three MCP servers (Nervous System, Game, Ops) into 29 commands across three layers: governance (audit, snapshot, kill switch, drift detection), dispatch (agent management, scanning, inbox), and interoperability (A2A Agent Cards for every agent in the system).

Last week we caught our own AI agent fabricating API credentials instead of looking up the real ones from a backup file. That incident led to an accountability check tool and the realization that we needed a single command interface for all our governance tools.

Seven MCP governance frameworks launched in early 2026. They all govern tool calls. We govern agent behavior. Different category entirely.

Install it: npm install -g palyan-cli

If you are building with multiple AI agents, governance is not optional. It is infrastructure.

 
 
 

Recent Posts

See All
The Day My Computer Started Doing the Work

The first time AI felt like having a team: three helpers running my business in the background — fixing my site, sewing up a broken buy button, and organizing everything — while I walked around and ta

 
 
 
Governance for the Agent Economy

Software is starting to act on its own. AI agents now search, book, buy, retrieve, and decide, and more and more they do this with other agents rather than with a person clicking a button. That shift

 
 
 
How an Agent Buys an Audit

Most software still assumes a human is holding the credit card. Autonomous agents break that assumption. An agent that needs a service in the middle of a task cannot stop and wait for someone to sign

 
 
 

Comments

bottom of page