Quota management logic found in DeepSeek web version code points to 'Coding Plan,' but no official announcement exists

The DeepSeek Harness team reported that on November 4th, the open-source agent execution environment from DeepSeek had 1.54 million daily active users. This information was presented in an update on November 5th, according to reports from IT Home and MyDrivers.

The count includes only users who utilize the product through the official DeepSeek API. This entire user base consumes approximately 92 trillion tokens per day.

These figures demonstrate the rapid growth of the product, which has existed for less than three months. The DeepSeek Harness v0.1 version was launched on August 13th, and the desktop version appeared on September 29th. As noted by MyDrivers, the number of active users was approximately 271,000 on September 30th, representing more than a fivefold increase in the user base in less than a month.

A significant portion of the activity is driven by plugins. According to the team, about 35,000 third-party plugins have emerged since the launch, and roughly 60% of active users have created or installed at least one of them. This aligns with the core concept of the product, which often boils down to the idea that everything is a plugin: models, tools, skills, sessions, sandboxes, storage, cycles, planning, and user interfaces are assembled from plugins that users can modify and combine.

As part of the update, the team also outlined future plans. They plan to improve the stability and compatibility of plugin APIs, strengthen plugin security mechanisms, and create an official plugin marketplace. This will allow authors to publish their plugins more easily and users to find the solutions they need.

Furthermore, a support program for plugin developers is being prepared, which will offer incentives in the form of tokens, technical interaction, and dedicated placement for their work. Details of this program will be shaped based on community feedback and needs. DeepSeek has also invited startups and companies to integrate their products, services, and specialized capabilities into Harness as plugins and consider partnerships. The official marketplace will provide the plugin ecosystem with a centralized distribution point for the first time, complementing existing community indexes and repositories.

The DeepSeek Harness team has made dsh-superagent publicly available—a research prototype that accepts development requests via GitHub and, optionally, via Feishu. The agent performs work in separate sessions and returns results, such as pull requests, back to the original conversation.

This prototype is configured around a single GitHub repository and functions as a package for DeepSeek Harness. It transforms authorized requests into working tasks, allocates a dedicated working directory and agent session for each task, and provides a web dashboard to display issues requiring human attention.

The project explores the capabilities of coding agents to complete long-running tasks with reduced need for human coordination. The implementation, which originated from the team's daily workflow, has been published and is available under the MIT license.

The DeepSeek Harness team has published a description of their project, which they named the Super Agent. This agent is designed as a continuously operating system that simultaneously advances multiple tasks, independently seeks work, and recovers from failures. The corresponding research prototype was released on GitHub under the MIT license, according to Chinese tech media.

The dsh-superagent-prototype repository is a package of a proactive coding agent intended to work with a single GitHub repository within the DeepSeek Harness ecosystem. The agent monitors activity on GitHub, and optionally on Feishu. When an authorized user requests a task execution, the agent creates a work item, processes it in its session and catalog, and then responds in the original dialogue, for example, by creating a pull request.

The accompanying documentation emphasizes that this code is for research purposes and is not an official DeepSeek product, and some concepts described in the document have not yet been implemented.

System Architecture

The core concept is built upon a two-layer architecture. The Router session receives all human activity from different channels but does not perform the work and may not even have a Bash tool. Tasks are delegated to isolated Worker agent sessions, which execute work in parallel using a full set of tools, and send reports back to the Router, bypassing communication with users.

Each Worker agent subscribes to branches of interest, such as chat discussions or pull requests, allowing subsequent events to go directly to it without passing through the Router. The system functions based on events: triggers include messages in chats, emails, review comments, and Continuous Integration (CI) results, which are first filtered by deterministic code and then by the model.

The team also separated the agent's state and the execution environment so that the agent can remain active in the cloud while interacting with the user's local machines. An external Watchdog session is also used to monitor whether the Worker agents are making real progress. Within the internal user group, the team established a rule: the instance must silently reproduce reported errors and only report them after finding a simple solution, sometimes opening a pull request before anyone flags the issue.

During preliminary tests on synthetic loads, including about 300 messages and approximately 20 work requests, the Super Agent completed half of the tasks in 12.4 minutes and 95% in 15.7 minutes. These figures surpassed the results achieved by a single session with a sub-agent tool, although they required more cached tokens. Without direct routing of subsequent events to the Worker agents, the Router's solutions increased by approximately 30%, and batch processing under high load reduced the time to output one Router solution from 6.4 seconds to 1.6 seconds. The team called these results a preliminary benchmark.

Among the unresolved issues listed by the team are scaling the Router, long-term memory, inter-agent communication, and the risk of prompt injection if the cloud agent gains access to credentials on local devices.