Alibaba's Qoder allows sending coding tasks from one desktop client to another device without using SSH
Read more
Pandaily
pandaily.com

Alibaba's Qoder allows sending coding tasks from one desktop client to another device without using SSH

Alibaba has introduced the 'desktop interconnect' feature in its Qoder product, which enables users to link a standard Qoder desktop client with a Qoder instance running on another computer. According to IT Home on October 30, users can now initiate tasks on a remote machine, track their progress, add requirements, and view the resulting outcomes.

Previously, Qoder already allowed remote management of a desktop device via a mobile application. The new feature aims to solve common developer challenges. For example, long operations such as project refactoring are often performed on more powerful dedicated hardware, while daily work is done on a lightweight laptop. Furthermore, builds, tests, and validations requiring a specific operating system or greater performance can be launched on separate devices.

Until recently, this required the use of SSH, which necessitates configuration, or a remote desktop, forcing users to constantly switch screens and search for the correct Qoder session. With 'desktop interconnect,' two devices connect directly, bypassing the need for SSH setup or other remote connection methods. After connecting, users continue working in the familiar client, launching remote jobs, checking progress, and providing instructions.

Files created by the remote agent, such as PowerPoint presentations or Excel spreadsheets, can be previewed on the local computer. Qoder states that eliminating the overhead associated with connection and switching allows users to focus on achieving goals, results, and key decisions.

In terms of security, the connection requires entering the device address and a special pairing code. Both devices must be authorized under the same account and complete the pairing process. Pairing codes are only valid for a limited time. Users have the option to select which workspaces to open and set synchronization permissions for existing sessions, thereby controlling access from the paired device. Connections can be terminated at any time, and device authorizations can be revoked when they are no longer needed.

The Qoder product family now includes a desktop application, an AI-enabled IDE, a command-line tool, a JetBrains plugin, the QoderWake digital employee product, and Cloud Agents. Alibaba reports that Qoder is used by over 8 million users and more than 100,000 corporate clients worldwide. This update is part of a series of releases aimed at expanding Qoder's capabilities across various devices and operating systems.

Similar stories

Doubao Work provides access to Kimi, GLM, and DeepSeek models for corporate clients
Read more
pandaily.com

Doubao Work provides access to Kimi, GLM, and DeepSeek models for corporate clients

Doubao Work, ByteDance's artificial intelligence agent application, announced on October 29th that it is expanding its functionality by providing access to third-party models for business clients. The first group of integrated models includes Moonshot AI's Kimi K3.1 Pro, Zhipu's GLM-5.3, and DeepSeek-V4.1-Flash. These models are now displayed in the application's model list alongside Doubao's proprietary models from ByteDance.

This update applies to team and enterprise subscription plans and is activated by default. Companies are not required to purchase separate access rights from each model developer or submit individual applications. Resource consumption is deducted from the AI credits that the organization already holds in Doubao Work.

Model Access Management

Administrators gain the ability to control which users can use a specific model. They can grant access to individual members, departments, groups, or the entire company. Furthermore, administrators can enable all models from one provider simultaneously or configure the use of a single specific model.

This move changes the positioning of Doubao Work. Previously, the application primarily served as a demonstration of ByteDance's Doubao models within an agent capable of interacting with files, browsers, and desktop applications. By allowing enterprises to direct tasks to competing Chinese models, the core product becomes the agent itself, rather than the underlying model. This also allows teams to choose a model based on the task type, such as using a coding-oriented model for engineering work and another model for handling long documents.

This development aligns with a broader trend among Chinese desktop agent products. This week, Xiaomi added DeepSeek, GLM, Kimi, and Qwen models to its MiMo Desktop, and several other agent tools have made similar moves. For enterprise-level buyers, a unified billing system and standardized permissions for multiple model developers significantly simplify the procurement process, which previously required comparing solutions from different manufacturers.

Doubao Work is continuously expanding its feature set. In recent weeks, capabilities such as saving recorded computer actions as reusable skills, importing chat history, skills, and memory from other AI tools with a single click, and an infinite creative canvas have been added. The application also supports parallel agents and local graphical interface control on Mac.

ByteDance has not specified what other third-party models will follow this initial batch, describing the current composition as the first group of models joining the platform.

ByteDance introduces developer assistant TRAE Bao with cross-project memory and chat features
Read more
pandaily.com

ByteDance introduces developer assistant TRAE Bao with cross-project memory and chat features

ByteDance's AI product TRAE has released a personal assistant for developers named TRAE Bao. This feature became available on October 29th. TRAE announced the launch through its official channels and on the official Chinese community forum.

Unlike the previous format, where the assistant performed one task per session, the new tool is designed to track the developer's projects, tasks, and decisions over time.

TRAE explains the problem as follows: a significant portion of the time developers spend with AI-based coding tools is not spent writing code, but rather on project detailing, task distribution, and switching between work sessions. With every new task, they have to re-explain the technical stack, project background, and previously made decisions. Complex requirements must be manually broken down, tracked across sessions, and then compiled.

The assistant uses a two-layer architecture. The global assistant is responsible for coordination and storing memory across different projects. It can analyze past tasks, dialogues, and the developer's work results, extracting reusable solutions and constraints. When a developer starts new work and defines a goal, the global assistant automatically loads the relevant context by studying experience from earlier projects.

The project assistant, conversely, focuses on one project at a time. Working within the context of that specific project, it breaks down a complex need into a series of actionable tasks, runs subtasks in parallel, integrates them, and summarizes the results. According to TRAE's description, the developer's role in this process shifts towards receiving reports and making decisions.

In the desktop application, access to the global assistant is available through a dedicated entry point, while creating or opening a project activates the project-level assistant. The global assistant can be integrated with messengers such as Feishu and WeChat, allowing developers to assign tasks and receive progress updates without opening the client application.

There are certain limitations: the current version only supports local tasks. TRAE has stated that support for cloud tasks and mobile devices will appear in future updates. Users on the official forum note that the feature is being rolled out gradually, first appearing in the Chinese version, and that an automatic model selection is currently used without manual configuration capability.

This launch adds TRAE to the growing group of desktop agents that allow users to delegate work from phones or chat applications and maintain long-term memory between sessions.

Alibaba's Qoder Platform Adds Support for LoongArch from Loongson Alongside UOS and Kylin
Read more
pandaily.com

Alibaba's Qoder Platform Adds Support for LoongArch from Loongson Alongside UOS and Kylin

Alibaba's coding platform Qoder now releases builds for Linux ARM64, as well as for the Loongson LoongArch64 instruction set. Furthermore, it has been adapted for the UnionTech UOS Desktop V20 and Galaxy Kylin Desktop V10 desktop systems. The company announced that both the international and Chinese versions received this update on October 23rd, enabling the end-to-end agent workflow from demand to delivery on desktop computers, which is already used by many government and corporate users in China.

The addition of LoongArch support is a significant point in this announcement. Modern Loongson chips utilize a fully self-developed instruction set that is neither ARM64 nor x86, and is not licensed by either party. Releasing the core coding agent for this ISA represents a tangible step in the software stack: developers can invoke tools, edit files, and perform multi-agent tasks on LoongArch machines without needing to switch to a workstation with a foreign architecture.

Support for Linux ARM64 covers a wider range of Arm-based PCs and boards within the same release series. Qoder was first launched globally in August 2025 as an agent-enabled coding platform, including a desktop IDE, CLI, and JetBrains plugins. In May 2026, Alibaba Cloud transformed it from an AI-IDE into a standalone development workstation called Qoder 1.0, and the former assistant Tongyi Lingma was integrated into the productive line for China as Qoder CN. The product family now also includes a mobile client, the QoderWake digital employee tools, and Qoder Cloud Agents.

Alibaba claims that as of August 2026, the product had over 6 million users and more than 100,000 enterprise clients; these adoption figures are company data. With this release, Qoder's presence on desktops in China now covers HarmonyOS PC and HarmonyOS mobile clients, as well as UOS V20 and Kylin V10. For teams using these systems, the practical change is that agent assistance in coding no longer requires a separate x86 environment or cloud environment.

Download information is available on the Qoder website, which provides installation instructions for Linux specifying the new architectures. The essence of this event is not so much the appearance of a new model, but where the agent coding stack is ready to operate. Placing LoongArch alongside ARM64 in one announcement clearly emphasizes the distinction: one line relates to Arm, the other to Loongson's proprietary ISA, and both now receive a first-party Qoder build.

Popular