wiki / entities / deepseek
DeepSeek
Machine ingest — raw context
loading…
~… tokensappend .md to any wiki URL for this view
DeepSeek
DeepSeek is an AI research and engineering company known for frontier open-weights models and open-source infrastructure. In 2026, DeepSeek released the DeepSeek Harness developer preview, advancing the architecture paradigm of Agent = Model + Harness.
Key Contributions to Agent Architecture
DeepSeek structures agent systems by separating the reasoning engine from the operational execution layer:
- The Model-Harness Split: DeepSeek formalized that while “the model is the soul of an agent,” the harness is what allows an agent to understand its environment, operate tools, and maintain durability in real-world environments.
- Microkernel Plugin Architecture: In DeepSeek Harness, DeepSeek adopted Cordis as an in-process microkernel where every agent subsystem (models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and UI) is implemented as a hot-pluggable service.
- Traceability & Deterministic Replay: DeepSeek emphasizes append-only session event streams, ensuring every context injection, tool call, reasoning trace, and subagent invocation can be inspected, forked, resumed, and replayed from the same stream.
Related Pages
Evidence — verified primary sources
| deepseek-harness-preview-2026 | https://deepseek.com/harness/en/ | ingested 2026-08-24 sha256:d4c5c87f4ed7… |
| deepseek-harness-cordis-primer-2026 | https://deepseek-harness.github.io/deepseek-harness/reference/cordis-primer | ingested 2026-08-24 sha256:e76a43328989… |