AI Features

Open and use the NetStacks AI assistant: the docked panel, full chat tab and pop-out window, the input bar selectors, tool-call results, approvals and chat history.

How the AI panel's Mode (Auto Pilot / Overlord) and Permission (Ask / Auto / Go Nuts) selectors work, which tool calls need approval, and how to enable, disable or rename tools.

The layers that limit what the NetStacks AI can do on your devices: approvals, the read-only command filter, AI Configuration Mode, AI Terminal Mode, the bash deny list and AI-generated script approval.

Connect NetStacks to an LLM: provider setup in the standalone Terminal (Anthropic, OpenAI, OpenRouter, Ollama, LiteLLM, Custom) and Controller-managed providers with priority and failover.

AI features that work outside the chat panel: command autocomplete, next-step suggestions, the terminal right-click AI menu, Tab-to-fill form fields, inline editor edits, the script generator and other AI buttons.

Let the AI watch terminal output live and highlight errors, security issues and anomalies, then click a highlight to discuss it with the assistant.

Record the commands and output from one or more terminals while you troubleshoot, then let the AI write the incident report for you.

Save the questions you ask the AI over and over, pin favourites to the AI panel, and customize the system prompts behind each AI mode and task.

Give the AI assistant a name, working style, expertise and safety rules. Standalone users build their own profile; Controller admins publish profiles that users pick from.

How the AI assistant knows what is on your screen, what it remembers between conversations, and how to give it standing knowledge about your devices.

What NetStacks sends to your AI provider, where it goes, and how credentials and other sensitive values are redacted before they leave.

Connect Model Context Protocol (MCP) servers so AI tools from other systems are available in NetStacks: in the standalone Terminal for the AI assistant, and on the Controller for Controller-side use.

Run AI agents as background tasks: define agents with their own system prompt, give them a task, and review the result. Covers the Terminal Agents panel and Controller agents.

The Controller's searchable knowledge base: where its content comes from, how it is indexed, how the AI uses it, and the Controller AI Chat that answers questions from it.

Crawl documentation websites into the Controller knowledge base so the AI can search vendor guides, internal wikis and standards.

Track and limit AI token consumption: per-response limits and usage counters in the Terminal, and the monthly token budget and Token Analytics on the Controller.

Quick Calls are saved HTTP requests against your API Resources (NetBox, LibreNMS, any REST API) that you can run from the status bar in one click.