Skip to main content
Version: dev

Rossoctl documentation

Rossoctl is an open-source platform that runs AI agents on Kubernetes. It gives each agent an identity that the platform can verify. It controls which services the agent can reach. It records what the agent did.

Rossoctl does not replace your agent framework. Your agent runs on Rossoctl without a change to its code, if the agent uses the A2A protocol.

Where to start

Your goalStart hereTime
See the model calls and tool calls that your agent makesQuickstart on a laptop5 minutes
Understand the token counts and the cost of a sessionRead the numbers
Run the platform and deploy an agentQuickstart on Kubernetes20 minutes
Put your own agent on the platformBring your own agent
Review the security modelSecurity
Find a command or a fieldReference

If you do not know which quickstart to use, read Get started.

The three parts of Rossoctl

RossoCortex is the data plane. It is a proxy that runs next to each agent. All traffic between the agent and an external service goes through this proxy. The proxy applies the identity checks and the access rules. See RossoCortex.

Services are the parts that an agent uses to do work. They include tools, skills, sandboxes and memory. See Concepts.

Tools for operators include the web console, the rossoctl command-line interface and the Kubernetes operator. See Install and operate.

What Rossoctl gives you

  • An identity for each agent. SPIRE gives each agent a cryptographic identity. The platform identifies the agent before it permits an action.
  • Access by delegation. An agent that calls a tool for you receives a token. The token is valid only for that tool. The token gives the agent no more permissions than you have.
  • Deployment without a code change. Give Rossoctl a container image or a Git repository. Rossoctl builds the agent, starts it and adds it to the platform.
  • A record of each action. Rossoctl collects traces, network data and token costs for each agent.

Maturity

Some features are ready for production use. Others are experiments. Read Concepts for the status of each feature before you depend on it.