AI Agents

Overview

Run AI coding agents in isolated workspaces. Each agent works independently without interfering with others.

Supported Agents

• Amp - Amp Code CLI
• Claude Code - Anthropic's CLI
• Codex - OpenAI's assistant
• OpenCode - Open-source alternative
• Pi - Minimal terminal coding harness
• Gemini CLI - Google's CLI agent
• Cursor Agent - Cursor AI agent

Chat

Superset includes a built-in chat panel for AI interactions without leaving the app.

• Use the model picker to choose supported models and connect providers
• Chat session titles are generated automatically from the conversation
• Use the thinking level control to set reasoning effort: Off, Low, Medium, High, or Max

Agent Settings

Go to Settings → Agents to customize launch behavior for each built-in agent.

• Enabled - Show or hide the agent in launchers
• Command (No Prompt) - Base command for terminal agents
• Command (With Prompt) - Prompt-aware command for terminal agents
• Prompt Command Suffix - Optional flags appended after the prompt payload
• Task Prompt Template - Template used when launching an agent from a task
• Model Override - Optional model override for Superset Chat
• Reset to Defaults - Restore the shipped configuration for that agent

Usage

Run agents directly in the terminal:

claude "Add error handling to fetchUser"

Auto-Run Command

When launching an agent from a task, the Auto-run command toggle controls whether it executes immediately.

• On - Terminal agents run their command right away, and Superset Chat sends the task prompt immediately
• Off - Terminal agents stage the command without pressing Enter, and Superset Chat opens as a draft instead

The setting is remembered between sessions.

Parallel Agents

Create multiple workspaces and run an agent in each. Compare results and merge the best solution.

Inline Prompts

Agents can pause and ask questions, request tool approval, and ask for plan review directly in the chat pane.

Sandbox Access

When an agent needs access to files outside its workspace, it will prompt for permission in chat so you can approve or deny the request inline.

Notifications

Get notified when agents finish. Configure sounds in Settings.