Alibaba Cloud introduces Memory service for long-term memory in personal agents

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.

The Qwen team from Alibaba described the process of creating a personal agent, asserting that the next stage in the development of AI assistants depends on the coordinated operation of three components: the model, memory, and service ecosystem. Jiang Guanjun, Head of AI Algorithms Department in Qwen Alibaba's business unit, presented this concept on October 22 at the China National Computer Congress (CNCC) in Chengdu.

Jiang divided the evolution of AI applications into three stages: chat, agent, and assistant. In the chat stage, AI responds to user queries. In the agent stage, the system performs assigned tasks. The assistant, which he says is where the industry is heading, combines professional knowledge with the user's personal context, plans actions around the user's goals, and detects needs they have not noticed. He emphasized that a true personal agent must provide added value and offer proactive, individualized service.

He suggested that theoretically, a personal agent is capable of solving almost all daily problems in work, study, and personal life. However, the main obstacle is the system's ability to correlate its capabilities with the optimal path to solving each specific problem.

Model Development Approach

Regarding the model, Qwen focuses on stable task execution. The team developed what is called a user needs map covering over 30 major industries and detailed it down to more than 8000 atomic requirements for the model's capabilities. Industry experts were involved in evaluating and tuning the model.

Memory Mechanism

Jiang noted that a personal agent must ensure long-term understanding of the user, avoiding the simple accumulation of chat history, which increases noise and computational costs. Qwen constructs its memory based on the degree of event interconnectedness, storing and retrieving them at various levels. For example, an assistant that remembers an elderly user mentioned their pension can give more relevant advice when the same family later asks about finding a job for a child.

Role of the Ecosystem

Concerning the ecosystem, Jiang stated that as models and management methods improve, the ability to link and coordinate external services becomes crucial. Qwen creates a model-oriented open service ecosystem that integrates professional knowledge, tools, industry skills, and third-party agents, while also connecting to e-commerce, local services, healthcare, and education.

In his view, these three elements combine to provide proactive service: memory provides personal information, the model uses expert knowledge to determine needs and plan, and the ecosystem executes the work, such as tracking a patient's rehabilitation schedule or alerting to new financial risks for the user. This report represents the most detailed public description of the technical concept behind the Qwen Go! personal agent, which Alibaba opened for registration this month.

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.