Monako Glass is a revolutionary wearable tool designed for developers, creators, and power users who want to run AI coding agents hands-free from a heads-up display. Weighing just 48 grams, it is the world’s lightest smart glasses featuring a waveguide display, camera, and speakers. Unlike mainstream smart glasses that focus on passive consumption, Monako Glass is engineered for active project building. It leverages a bone conduction microphone, a vision engine, and an agent terminal to provide a unified, voice-and-gesture-controlled interface. The core value lies in enabling users to interact with AI agents and professional software without touching a keyboard or mouse, transforming how technical work is done in real-world environments.
Traditional input methods like keyboards and microphones struggle in noisy or mobile settings. When coding or designing, environmental chaos—traffic, office chatter, wind—interferes with voice commands and breaks concentration. Monako Glass solves this ‘input problem’ by using a bone conduction microphone that captures nasal vibrations, completely ignoring ambient sound. This ensures clear voice input even in loud spaces, making it ideal for commuting, fieldwork, or open offices. Additionally, micro gestures provide silent input for discrete commands. For developers and creators who need to stay productive while moving or in disruptive environments, this hands-free interaction removes friction and maintains flow.
The first major feature is the Bone Conduction Microphone, called the ‘world’s best mic for Typeless and Whisper Flow.’ By moving beyond air-borne sound, it isolates the user’s voice from background noise. This is crucial for ‘Typeless’—operating without a keyboard—and ‘Whisper Flow’—quiet voice commands. The microphone captures vibrations from the nasal cavity, providing crystal-clear audio regardless of external noise. This allows users to dictate code, issue commands to AI agents, or communicate in meetings from any location. The benefit is consistent, reliable voice input in chaotic settings, a game-changer for mobile professionals and those who prefer voice-driven workflows.
The second major feature is the AgentTerminal, which provides connectors for Claude Code, Codex, Unreal Engine, Blender, and After Effects. This transforms separate tools into a single cohesive workstation. Users can invoke an AI coding agent to write scripts, automate tasks, or generate 3D assets directly through the glasses. For example, a game developer can ask an AI to modify an Unreal Engine blueprint while walking across a studio. The AgentTerminal integrates these platforms into the glasses’ interface, allowing voice or gesture-based control. This eliminates context-switching and keeps users in the flow, dramatically speeding up complex workflows that normally require multiple screens and manual inputs.
admin
The third major feature is the VisionEngine, inspired by Apple’s Vision Pro. It translates micro gestures—tiny hand or finger movements—into precise digital commands. This allows for hovering, pointing, scrolling, and selecting without needing a physical controller. Combined with the bone conduction microphone, users have two parallel input channels: voice for high-level commands and gestures for fine control. The VisionEngine uses the glasses’ camera to track gestures with low latency, making interaction feel natural and instantaneous. This is especially useful for photo and video editing, 3D modeling, and navigating complex interfaces where pinpoint accuracy is needed without a mouse.
Monako Glass runs MonoOS, the world’s first Linux distro with a Lua-based application layer and an embedded Rive animation runtime. LuaJIT requires only 200–500 KB of RAM per app, ensuring high performance with minimal overhead. Agents can generate Lua apps on the fly and execute them instantly without compilation—no build step needed. The Rive runtime provides lightweight, interactive vector animations that are state-driven and fast, enabling cinematic interface motion on wearable hardware. MonoOS also supports hyper-personalized apps that users can ‘speak into existence’ and share as real server-backed experiences. Seamless interop allows workflows to span Monako Glass, cloud sandboxes, and local Mac/PC, creating a truly connected ecosystem.
In practice, Monako Glass is used for building projects hands-free. A developer on a train can use voice to create a React component via Claude Code, see the code appear in the waveguide display, and approve it with a micro gesture. A 3D artist can walk around a workspace while modifying Blender scenes using voice prompts and gestures. Video editors can trim clips in After Effects by pointing and speaking. The outcome is faster iteration, reduced physical strain, and the ability to work from anywhere. Users report staying in deep focus because they never need to reach for a device. The hands-free paradigm also enables multitasking—like checking code reviews while walking or monitoring AI agent progress while making coffee.
Monako Glass targets developers, AI researchers, 3D artists, video editors, and any professional who uses heavy computing tools on the go. It integrates with Linux, Mac, and PC via seamless interop. The reservation price is just $19, signaling an accessible early-bird model. The tech stack—Lua, Rive, Linux, and connectors to major creative and coding platforms—ensures broad compatibility. By solving the input problem with a bone conduction microphone and gesture recognition, and by providing a dedicated operating system for wearable productivity, Monako Glass offers a glimpse into a future where AI agents are always accessible. It is a tool for those who want to ‘see more, do more, be more’ without being tethered to a desk.
Software developers who want to code hands-free while mobile, AI researchers needing always-on agent interaction, 3D artists and Blender users who work away from desks, video editors using After Effects, game developers working with Unreal Engine, and any technical professional seeking to reduce physical strain and context-switching by leveraging voice and gesture control through a lightweight wearable.