Requests with an accountable source
GitHub and optional Feishu events enter a policy-controlled routing process. Allowed senders, receiving scope, and team rules determine whether a request can become work.
DSH Superagent Prototype
Explore DeepSeek’s research prototype for turning authorized GitHub and Feishu requests into coding tasks. Study task routing, scoped execution, and reviewable delivery for your own agent workflows.
About DSH Superagent Prototype
DSH Superagent Prototype is a proactive coding agent published in DeepSeek’s official GitHub organization. It runs as a DeepSeek Harness bundle for one GitHub repository, with optional Feishu input. Authorized requests become tasks that execute in their own sessions and working directories, then return results to the original conversation.
Its useful workflow patterns include evaluating incoming requests, keeping each task within an assigned scope, and following discussion without treating every message as new authority. The web panel prioritizes work needing a person and also exposes history and operational health.
The MIT-licensed repository is research code, explicitly described as not an official DeepSeek product or production-ready software. Its published implementation differs from the internal version and the accompanying design article; some ideas discussed there remain unimplemented.
How Requests Become Agent Work
Follow the mechanisms that connect a team’s request to a bounded task and a result someone can review.
A scope for each task
Accepted work becomes a Ticket with a Mandate defining its authority. Its executor uses a dedicated session and directory while subscribed conversations provide continuing context.
Results where the work started
The agent can reply in the original conversation and open pull requests. A panel brings review, blocked work, and other items needing human attention into view.
Workflow Ideas to Try
Use these patterns to improve coordination around your own tasks, then verify any software integration separately.
Repository maintenance requests
Define a small coding request, its permitted changes, and the evidence needed for acceptance. Use the task-to-pull-request pattern to make the proposed result easy to inspect.
Follow-up after a review
Keep a reviewer’s comments attached to the right task and preserve the original scope. Route requests for unrelated work separately instead of silently expanding an existing assignment.
Team messages with a clear outcome
Specify which channel and people may request work, then define where the result should return. Borrow that handoff pattern for workflows organized in Floatboat without assuming a built-in connection.
Before Running the Prototype
Check the runtime, account, and machine boundaries before moving from a design reference to a live experiment.
- 01
Prepare the runtime and agent identity
Use a supported Harness version, a configured model provider, and the documented command-line dependencies. One deployment serves one github.com repository through a dedicated GitHub user account.
- 02
Separate machine permissions
The documented router and worker presets run with full access as the operating-system user. Separate sessions and credential wrappers are not a sandbox; use a dedicated OS account for isolation.
- 03
Inspect inferred work first
The default observe mode records inferred tasks it would accept without starting them; explicit requests still execute. Review decisions before enabling automatic acceptance under written rules.
From GitHub Requests to Agent Workflows
Trace a request through authorization, task execution, and delivery, then decide which mechanisms fit your own workflow.
Related Agent Projects
Compare independent agents through their interfaces, extension models, and approach to carrying work forward.
DSH Superagent Prototype FAQ
Is DSH Superagent a DeepSeek model?
It is agent application code running on DeepSeek Harness. A separately configured model provider supplies inference; the project itself is not model weights or a model API subscription.
How does it differ from DeepSeek Harness?
Harness provides the surrounding agent runtime and extension system. Superagent is a bundle built on that runtime to coordinate requests, tasks, sessions, and delivery for a repository.
Does it need Feishu or support every GitHub deployment?
Feishu is optional. The documented scope is one github.com repository per deployment; GitHub Enterprise Server is unsupported. The agent needs a dedicated GitHub user with write access, rather than a GitHub App.
Does observe mode stop every task from running?
No. It evaluates inferred candidates and records positive assessments without accepting them. Explicit requests work in every mode; automatic acceptance of inferred work requires auto mode and matching rules.
Are workers isolated from the rest of my computer?
No security sandbox is provided by the separate task directories or account wrappers. The documented presets run with full OS-user access, so the deployment guide recommends a dedicated OS account containing only the agent credentials.
Does MIT make it production-ready or include free inference?
MIT covers the source code. Model services and machine operation have separate costs and terms. The README identifies the software as a research prototype, with differences from its internal implementation and some unimplemented design ideas.