THE WORLD'S FIRST CLI WITH
NATIVE TERMINAL SPLIT PANEL.

The first CLI tool with native Windows Terminal split panel mode. Run Claude, GPT, and Gemini agents in parallel panes — no tmux required. Also supports iTerm2 on macOS.

Install AemeathCLI View on GitHub

src/core/model-router.ts esc when done

                        12
                        export const resolve = ({ role, ctx }) => {
                    
                        13
                          const config = loadRoleConfig(role);
                    
                        14
                          const primary = config.primary ?? defaults[role];
                    
                        15
                          if (isAvailable(primary)) return primary;
                    
                        16
                          return config.fallback.find(isAvailable) ?? ctx.default;
                    
                        17
                          return <ModelStream provider={primary} />;
                    
                        18
                        }

Features

01 — Windows

Native Windows Terminal Split Panel

The first CLI tool to leverage Windows Terminal's native pane API. No tmux, no WSL workarounds. Each AI agent runs in its own parallel pane with real-time IPC coordination and shared board state.

AemeathCLI running multiple AI agents in split panels on Windows Terminal

02 — macOS

iTerm2 Native Pane Integration

Seamless split panel orchestration through iTerm2's native AppleScript API. Hub-and-spoke coordination with shared board directory and real-time message passing between agents.

AemeathCLI split panel orchestration on macOS with iTerm2

03 — Orchestration

Multi-Model Agent Swarm

Describe your task in plain English. The LLM designs the optimal team — choosing models, roles, and prompts. Claude for architecture, GPT for implementation, Gemini for review.

AemeathCLI welcome screen showing the Aemeath Agent Swarm interface

Agent Teams

LLM-Designed Agent Teams

Describe what you need in plain English. The LLM analyzes your prompt and designs the optimal team — agent count, roles, models, and task prompts.

Create a team to refactor the auth module

I need agents to review this PR from different angles

Spawn a team to build the payment feature

Split-Panel Output

> Analyzing team request... Done

> Designed 3-agent team:

AuthArchitect (claude-opus-4-6) — planning

Refactorer (claude-sonnet-4-6) — coding

SecurityReviewer (gpt-5.2) — review

> Split-panel active ✓

/team stop to exit

THE WORLD'S FIRST CLI WITH NATIVE TERMINAL SPLIT PANEL.

Native Windows Terminal Split Panel

iTerm2 Native Pane Integration

Multi-Model Agent Swarm

LLM-Designed Agent Teams

THE WORLD'S FIRST CLI WITH
NATIVE TERMINAL SPLIT PANEL.