Hasso Monjo · Flagship Product · Early Access

Two frontier models.
One codebase.

Monjo runs two Anthropic frontier models simultaneously on your project — one sandboxed for deep reasoning and planning, one with full terminal and system access for execution. This workflow doesn't exist anywhere else.

Join the waitlist See Monjo pricing
Monjo · dual-model session · bypass: elevated
Sandbox — design + planning
$ indexing /src…
→ 847 files mapped
✦ writing styles
→ auth.css updated
→ tokens.css patched
→ JS plan → exec ↓
verifying output…
✓ styles confirmed
Exec — logic + terminal
[standing by]
✦ JS plan received
[1] auth/index.js
[2] $ npm i jsonwebtoken
[3] middleware/auth.js
[4–6] running…
Monjo is in active development. Content below uses placeholders — final feature set and pricing will be confirmed at launch. Join the waitlist for early access.
Architecture

The dual-model engine.

No other AI coding tool runs two frontier models simultaneously on one codebase. Monjo separates intelligence from execution by design — one model thinks, one acts, both run at the same time.

Simultaneous · Anthropic frontier only
Sandbox Model
Anthropic frontier · design + planning layer
Design language.
Architecture. Style.
  • Full codebase indexing & analysis
  • Task planning & edit sequencing
  • All CSS — styles, animations, tokens
  • HTML structure & markup
  • Design system & visual language code
  • Output review & verification
Executive Model
Anthropic frontier · logic + execution layer
Heavy code.
Real execution.
  • JavaScript & TypeScript logic
  • Backend languages — Python, Go, Rust…
  • Terminal & CMD execution
  • Package managers (npm, pip, cargo…)
  • Build systems, compilers & test runners
  • Process control & scripting
Your codebase — local, never uploaded, never shared
Capabilities

What Monjo can actually do.

This is not a coding assistant. Monjo is an autonomous agent with real system access — the gap between "suggests changes" and "ships them" is the entire point.

Simultaneous dual-model execution

The sandbox model writes CSS, HTML, and design language code while simultaneously planning the JS logic for the exec model. The exec model handles all JavaScript, backend languages, and terminal commands. Both run at the same time — one builds the visual layer, one builds the logic layer.

🗺

Deep codebase awareness

The sandbox model maps your entire project — imports, dependency graph, build config, test suites — before touching a single file. It understands your architecture the way a senior engineer would.

⚙️

Tiered bypass permissions

Standard: file edits only. Elevated: + terminal, CMD, and package managers. Full: complete autonomous system control. Monjo operates exactly within what you grant.

🖥

Full terminal + CMD access

At elevated bypass, the exec model has real shell access — npm, pip, git, compilers, test runners, build scripts, any CLI your project needs. It runs them, not simulates them.

🔒

Fully local — code never leaves

Monjo is a native Windows Electron app. Your codebase is never uploaded, synced, or sent to any server. Only AI inference calls leave your machine.

🔗

Hasso ecosystem integration

Pair Monjo with Hasso Build and AI for a complete pipeline — from AI-generated site to production-ready codebase, all within one platform.

How it works

How the dual-model engine runs.

Both models fire simultaneously from the moment you start a session. The sandbox model never slows the exec model down — they operate in parallel, coordinating in real time.

01

Define the task

Give Monjo an engineering brief in plain language. It treats it as a real task — not a chat message. Set your bypass level before execution begins.

02

Sandbox writes the visual layer

The sandboxed model indexes the codebase, plans all changes, and immediately starts writing — CSS, HTML, design tokens, animations, component markup. The full visual layer, no terminal needed.

03

Exec writes logic + runs terminal

Simultaneously, the executive model receives the JS/TS plan and executes — writing application logic, backend code, running npm installs, build scripts, and any terminal commands the task requires.

04

Continuous cross-model coordination

The sandbox verifies exec output, catches logic errors, and adjusts styles to match new code structure — all in real time. Both models stay in sync throughout the entire session.

System requirements

Built for Windows. Optimized for speed.

Monjo runs as a native Electron app. No Docker, no cloud dependencies, no setup beyond the installer.

Platform Windows 10 / 11 (64-bit)
Runtime Electron · Node.js bundled
RAM 8 GB minimum · 16 GB recommended
Disk 500 MB installer · project files local
Code stays on device ✓ Always local
AI architecture Dual frontier model (simultaneous)
Model provider Anthropic only — no other providers
Sandbox model Reasoning · planning · no system access
Executive model Full terminal · CMD · file system
Internet required For Anthropic API calls only
macOS / Linux Coming later
Pricing

Early access pricing.

Monjo is in early access. Pricing below is indicative — confirmed at launch. Join the waitlist for founding-member rates.

Monjo Solo

$49 /mo
  • 1 machine license
  • Autonomous code agent
  • Tiered bypass permissions
  • Full terminal + CMD access
  • Windows Electron app
Join waitlist

Monjo Agency

$149 /mo
  • 3 machine licenses
  • Shared session history
  • Team bypass policy controls
  • Agency 3 plan included
Join waitlist

Pricing is preliminary and subject to change before launch.

Early access

Be the first to run Monjo.

Join the waitlist for early access, founding-member pricing, and direct input on what Monjo builds next.

No spam. Unsubscribe any time. Windows-first — macOS and Linux coming later.