DingTalk opens source code for DWS command-line tool for AI agents with HarmonyOS PC support

A team of innovators, overseen by the Xiaomi technology committee, has introduced HachimoDock—a small, desktop AI device that users can assemble and configure themselves. This was revealed after the device demonstration at the Guanqi Conference 2026 on October 26, according to sources IT Home and Sina Tech.

According to the team, the cost of components for self-assembly is approximately 150 yuan. The main goal of the project is to lower the barrier to entry into AI hardware and make HachimoDock the first device for those starting with 'vibe coding'—a method where the user describes what they want in simple language, and the AI generates the corresponding code.

HachimoDock combines a customizable desktop companion, voice control for computer agents, smart home management functions, and user-assembled components. When the user addresses the desktop companion, it translates the request into tasks and passes them to computer agents like Codex and WorkBuddy. These agents perform operations such as information retrieval, file organization, or code writing.

The device screen informs the user about the task execution status—thinking, running, or awaiting confirmation. Furthermore, the companion signals progress through facial expressions, movements, short prompts, and sounds. Operations requiring authorization still require confirmation via the relevant desktop client.

Voice control capabilities extend to the home environment through Xiaomi Miloco—the company's open-source AI framework for smart homes. The small display can transform into a home control panel, showing device status, lighting controls, and camera video feeds, allowing one desktop device to serve as an entry point for both PC agents and smart home devices.

Users can also instruct the AI to generate and launch new components on the spot. This allows HachimoDock to function as a microphone for voice input, a mini-console for gaming, an FM radio receiver, a secondary screen for monitoring AI task progress and computer status, or as a central hub for the smart home.

The source code is available on GitHub along with the hardware component specifications, structural part models, and assembly guides. However, there is an important limitation: the project is open-source, but not fully open in the common sense. The license permits personal, non-commercial reproduction, modification, and creation of components, but commercial use, integration, or development of separate products requires written permission from the copyright holders. Third-party components, including Xiaomi Miloco, retain their own licenses.

The team leader stated that they aim to provide a space for every user to define HachimoDock, so that more people can enjoy creating low-cost AI hardware.

Xiaomi has introduced MiDashengLM-Spatial, a new component of its Dasheng series of audio models. This model is designed not only to understand the content of sound but also its spatial origin.

The full model weights and inference code have been published by the company under the Apache 2.0 license, which permits both research and commercial use. The model is built upon MiDashengLM-7B, a large sound understanding model that Xiaomi previously made open source.

To enable spatial perception, a spatial audio encoder named Spatial-Dasheng was added to the model. According to a technical report posted on arXiv, it utilizes a hierarchical semantic-to-spatial conditioning module that separately captures semantic and spatial information before merging them. This results in a unified end-to-end model capable of analyzing speech, background noise, and music, as well as inferring the direction, distance, and movement of the sound source.

On the Hugging Face page, the model is presented with approximately 8 billion parameters. Spatial cues depend on multi-channel input; the model description states that it was trained on binaural two-channel audio, although mono input is also supported, it does not carry directional information.

Xiaomi asserts that the general audio capabilities of the model are preserved, and the research team reports that performance in basic audio processing tasks remains comparable to large audio-language models of around 8 billion parameters.

Xiaomi positions MiDashengLM-Spatial as the first open, end-to-end model for spatial audio understanding in the industry. It should be noted that this claim is contained within the article and qualified with the phrase 'to our knowledge,' and it has not yet been independently verified.

Over the past two years, Xiaomi has made its fundamental sound models, Xiaomi Dasheng and MiDashengLM-7B, open source. The company notes that technologies from the Dasheng series are already used in over 30 applications across its smart home and automotive cockpit products, covering speech recognition, ambient sounds, and music. This figure refers to the existing series, not the new MiDashengLM-Spatial model.

Regarding MiDashengLM-Spatial itself, Xiaomi plans to gradually integrate it into smart home and automotive cockpit scenarios, where knowing the origin of a voice or alarm signal will allow assistants to react more accurately. The company has not yet provided timelines or names of specific products.

The release includes a project demo page, a technical report on arXiv, evaluation code on GitHub, and model weights on Hugging Face.