Unverified50% confidenceFactExact time
The dsh-superagent chain contains seven core concepts: source, trigger, thread, evaluation, borrowing, authorization and dispatch.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
DeepSeek's Open-Source Agent Teardown: 11,700 Stars but Only One Commit
bilibili翻车老头11/3/2026
Related Entities
Related Claims
UnverifiedThe core architecture of dsh-superagent is a resident design that separates the Router from the Worker.73% similarUnverifiedThe core design philosophy of DSH is 'everything is a plugin,' abstracting capabilities such as large model invocation, tool integration, and skill orchestration into pluggable modules.69% similarUnverifiedDSupport's architecture divides responsibilities as follows: the model (non-deterministic) handles understanding natural language, deciding which tool to call, drafting replies, and routing between experts; the code (deterministic) handles validating types and rules, hiding sensitive data, blocking operations that must not be allowed through, and running offline tests.63% similarUnverifiedDSH提出核心公式：智能 = Model + Harness63% similarUnverifiedA DSH project typically contains system prompts, Skills, and the definition of the Agent.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1133480API
curl https://kongchang.com/api/v1/knowledge/claims/1133480MCP
get_claim(id=1133480)