Understand this story
On November 2, 2026, DeepSeek open-sourced a new project, dsh-superagen. According to a report by A Yi AI Notes, the project, in the form of a bot residing in a GitHub repository and a Feishu group, automatically captures requirements from Issues and group chats, generates tickets, and then writes code, runs tests, and submits pull requests on its own. Underneath, the project uses a multi-agent architecture in which a main router dispatches tickets and multiple parallel worker nodes execute them; each node is physically isolated through an independent Git worktree. The report says that in actual testing it cut the time for complex tasks from 29.5 minutes to 15.7 minutes; review comments on pull requests are automatically subscribed to and routed back to the original worker node. Another report the same day said that the system opens 3 work slots by default, supports 1 to 16 concurrent tasks at most, and always reserves 1 slot for humans to jump the queue; subsequent events for the same task are subscribed directly to the corresponding workstation. The author says it takes just 5 steps to get started. There are currently no further developments.
AI-generated from public reports
Latest development · Report
DeepSeek Open-Sources the dsh-superagent Multi-Agent ArchitectureDevelopments
1 confirmed developments
- Source:Ayi AI Notes
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 2
AYi AI Notes
DeepSeek Open-Sources the dsh-superagent Multi-Agent Architecture
DeepSeek has open-sourced the dsh-superagent multi-agent architecture, turning code repositories into automated pipelines: each repository is assigned a resident overall dispatcher (Router Session), which only reviews GitHub Issues, PRs, or CI errors and does not directly modify business code; after a task passes whitelist evaluation, the system spins up a separate Worker for it, assigning an independent session, an independent directory, and a git worktree branch for parallel execution. The system opens 3 work slots by default, supports a maximum of 1 to 16 concurrent tasks, and always reserves 1 slot for humans to jump the queue; subsequent events for the same task are subscribed directly to the corresponding workstation, bypassing the overall dispatcher to avoid repeatedly consuming Tokens. The author says it takes just 5 steps to get started.
Ayi AI NotesSelected
DeepSeek open-sources the dsh-superagen multi-agent development project
DeepSeek has open-sourced a new project, dsh-superagen, which acts as a bot residing in GitHub repositories and Feishu groups, automatically capturing requirements from Issues and group chats, generating tickets, and then writing code, running tests, and submitting pull requests on its own. Under the hood, the project uses a multi-agent architecture in which a main router dispatches tickets and multiple parallel worker nodes execute them; each node is physically isolated via its own Git worktree. In testing, it cut the time for complex tasks from 29.5 minutes to 15.7 minutes. Review comments on pull requests are automatically subscribed to and routed back to the original worker node, with no need for repeated manual summoning.
Analytics India Magazine
DeepSeek releases Super-agent architecture proposal, using a Router to schedule multiple coding agents
On October 31, the DeepSeek Harness team released a technical proposal titled "Exploring Super-agent Design: Towards a More Autonomous Agent System," proposing the use of a central Router to distribute tasks to Worker agents executing in parallel, in order to reduce the burden on developers of managing coding sessions one by one. In the simulated experiments, the 95th percentile task completion time for this architecture was 15.7 minutes, compared with 29.5 minutes for the single-session approach; each run involved about 300 messages and about 20 task requests, each configuration was tested 5 times, and the task workload was synthetic data, with coding tasks simulated by time-consuming tools, so what was measured was scheduling and coordination capability rather than coding capability. DeepSeek also open-sourced the research prototype dsh-superagent-prototype on GitHub under the MIT license, which supports a single repository and can optionally listen for Feishu messages, and stated that the prototype is not an official product and differs from the internal implementation, while also flagging security risks such as prompt injection and credential leakage.