Product

One control layer for your AI engineering crew

MUON sits between your engineering mission and the coding agents doing the work. It assigns bounded responsibilities, keeps context moving, tracks progress, and returns consequential decisions to your team.

See how the loop works

The platform contract

MUON runs the crew. Your team sets the mission, approves sensitive actions, and decides what ships.

Working surfaces

One mission record, however your team works.

Full workspace

Desktop

Mission chat, Crew, shared memory, approvals, changes, governed review, agent sessions, native terminals, and audit activity share one workspace-bound interface.

Complete control path

CLI

Onboard providers, run tasks, apply workflows, inspect status, review approvals, request a second opinion, run checks, and file merge approval from scripts or a terminal.

Operational parity

TUI

Observe the same jobs, gates, memory, workflow state, and panic-stop outcome in a keyboard-first interface designed for narrow terminal layouts.

Agent stack

Clear roles, governed by MUON.

Claude CodeCodexOllamaCursor
Claude CodeDispatch-ready

MUON can assign bounded implementation, investigation, repair, or review work and create governed child jobs with enforced lineage and limits.

CodexDispatch-ready

MUON can assign bounded implementation, investigation, repair, or review work and create governed child jobs with enforced lineage and limits.

CursorReadiness-only

MUON can detect the Cursor agent CLI and preserve a human-owned continuity path. Cursor is not a governed dispatch or QA lane in the current build.

OllamaOptional

A loopback Ollama instance can strengthen local memory recall without becoming a coding worker. MUON falls back to built-in lexical recall when it is absent.