[KongchangAI]
ProductDSH

DSH Super Agent

An open-source multi-agent collaboration framework from DeepSeek that adopts a two-tier Router-Worker architecture, emphasizing the scheduling and restraint of human attention, and includes mechanisms such as subscription passthrough, speculative execution, and Watchdog.

Timeline (last 90 days)

Nov 7

DSH Super Agent's architecture is divided into two layers: the upper Router layer receives messages, decomposes tasks and maintains global context; each lower-layer Worker has its own independent working directory per task, executing in parallel without interfering with each other.

Unverified50%
Nov 7

DSH Super Agent uses a "subscription pass-through" mechanism: after a Worker takes over a PR, it directly subscribes to that PR's comment stream, and subsequent comments are pushed directly to the Worker without Router forwarding.

Unverified50%
Nov 7

Cancelling the subscription pass-through channel increases the Router's number of decisions by 30% and the tokens for reading the cache by 37%.

Unverified50%
Nov 7

DSH Super Agent has two filters at the message entry: programmatic rules first screen out irrelevant messages, then the model decides whether to act; and the AI can ask only one specific question at a time, in the form of a structured form.

Unverified50%
Nov 7

DSH Super Agent separates compute, state and execution environment: inference runs in the cloud, session state is stored locally separately, and recovery after shutdown is supported.

Unverified50%
Nov 7

The first line of DSH Super Agent's readme states: this is a research prototype, not an official DeepSeek product, it may have bugs, the engineering style is inconsistent, and you need to modify it yourself for production.

Unverified50%
Nov 7

DSH Super Agent currently targets only a single GitHub repository, with optional Feishu integration.

Unverified50%
Nov 7

Some of the design prototypes mentioned in the DSH Super Agent paper have not yet been implemented.

Unverified50%

All Facts (8)

Unverified

DSH Super Agent's architecture is divided into two layers: the upper Router layer receives messages, decomposes tasks and maintains global context; each lower-layer Worker has its own independent working directory per task, executing in parallel without interfering with each other.

50%
Unverified

DSH Super Agent uses a "subscription pass-through" mechanism: after a Worker takes over a PR, it directly subscribes to that PR's comment stream, and subsequent comments are pushed directly to the Worker without Router forwarding.

50%
Unverified

Cancelling the subscription pass-through channel increases the Router's number of decisions by 30% and the tokens for reading the cache by 37%.

50%
Unverified

DSH Super Agent has two filters at the message entry: programmatic rules first screen out irrelevant messages, then the model decides whether to act; and the AI can ask only one specific question at a time, in the form of a structured form.

50%
Unverified

DSH Super Agent separates compute, state and execution environment: inference runs in the cloud, session state is stored locally separately, and recovery after shutdown is supported.

50%
Unverified

The first line of DSH Super Agent's readme states: this is a research prototype, not an official DeepSeek product, it may have bugs, the engineering style is inconsistent, and you need to modify it yourself for production.

50%
Unverified

DSH Super Agent currently targets only a single GitHub repository, with optional Feishu integration.

50%
Unverified

Some of the design prototypes mentioned in the DSH Super Agent paper have not yet been implemented.

50%

Source Articles