Skip to main content
All AI-powered features in mogenius — including AI Insights and AI Chat — share a single model configuration. Once you connect a model and configure limits, every AI feature on your cluster is ready to use.

​
Connecting an AI Model

Navigate to your Cluster page and open the AI tab. Click Configure AI and fill in the following fields:
  • SDK: Choose between OpenAI, Anthropic, or Ollama.
  • API Key: If the model endpoint requires authentication, enter an API key or token.
  • Model: Select your desired model from the dropdown. If no models appear, check your endpoint or authentication.
  • API URL: Enter the model endpoint URL. For OpenAI, the default is https://api.openai.com/v1. You may also use any OpenAI-compatible API endpoint.
After saving, mogenius will validate the connection and activate AI features across your cluster.

​
Token Limits

Set a Daily Token Limit to control how much the AI agent can consume per day. This limit is shared across Insights reports and Chat conversations on the cluster. Once the limit is reached, new Insights reports are queued and processed when the limit resets the next day. After configuration, the settings page displays additional admin controls: Token usage — Monitor today’s token consumption and see when the limit will reset. Reset token limit — Manually reset the token usage to zero. Delete all AI data — Deletes all existing insight reports from the local database and resets the token usage. The agent will start fresh.

​
Tools

The AI agent has access to built-in tools for interacting with your cluster, plus optional integrations you can enable.

​
Built-in Tools

These tools are always available once AI is configured:
  • Kubernetes — Query and inspect cluster resources such as Pods, Deployments, Services, ConfigMaps, and events. Read logs, describe resources, and retrieve manifests. Create new resources and manifests to deploy applications.
  • Helm — List and create Helm releases, inspect chart values, and review release history.

​
GitHub

Connect a GitHub repository to give the AI agent access to your codebase and enable the Memory Repository feature. To enable GitHub integration, navigate to the AI settings page and enter a Personal Access Token for your Github account.

​
Memory Repository

The Memory Repository is a GitHub repository that the AI agent uses to store and retrieve long-term context. You can use an agents.md file as a generic format to provide additional context on how the agent should behave within your organization. When enabled, the agent can persist knowledge across sessions — such as recurring issues, environment-specific configurations, or team conventions — and reference it in future analyses and conversations. To set up a Memory Repository, select a GitHub repository in the Tools configuration. The agent will use this repository to read and write context files that improve the quality of its responses over time.