---
title: "DeepSeek"
description: "AI research company behind frontier open-weights models and the DeepSeek Harness agent runtime developer preview."
section: "entities"
type: "entity"
created: "2026-08-24"
updated: "2026-08-24"
confidence: "high"
tags: ["company", "agents"]
canonical: "https://pyweb.dev/wiki/deepseek"
---
# 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:

1. **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.
2. **Microkernel Plugin Architecture:** In DeepSeek Harness, DeepSeek adopted [Cordis](/wiki/cordis-framework) 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.
3. **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
- [cordis framework](/wiki/cordis-framework)
- [deepseek harness](/wiki/deepseek-harness)
- [agent harness engineering](/wiki/agent-harness-engineering)
- [agent native infrastructure](/wiki/agent-native-infrastructure)
- [anthropic](/wiki/anthropic)

---

## Agent Navigation

cluster: person (170 pages) | betweenness: 12.7

### References (outbound)
- [Cordis Framework](https://pyweb.dev/wiki/cordis-framework.md)
- [DeepSeek Harness](https://pyweb.dev/wiki/deepseek-harness.md)
- [Agent Harness Engineering](https://pyweb.dev/wiki/agent-harness-engineering.md)
- [Agent-Native Infrastructure](https://pyweb.dev/wiki/agent-native-infrastructure.md)
- [Anthropic](https://pyweb.dev/wiki/anthropic.md)

### Referenced by (inbound)
- [Cordis Framework](https://pyweb.dev/wiki/cordis-framework.md)
- [DeepSeek Harness](https://pyweb.dev/wiki/deepseek-harness.md)
- [OpenAI](https://pyweb.dev/wiki/openai.md)

### Evidence (verified primary sources)
- [deepseek-harness-preview-2026](https://pyweb.dev/wiki/raw/articles/deepseek-harness-preview-2026.md) | origin: https://deepseek.com/harness/en/ | ingested: 2026-08-24 | sha256: d4c5c87f4ed70dd2bed5051988a96c07050c9dbcefa519e034c72da971a9747c
- [deepseek-harness-cordis-primer-2026](https://pyweb.dev/wiki/raw/articles/deepseek-harness-cordis-primer-2026.md) | origin: https://deepseek-harness.github.io/deepseek-harness/reference/cordis-primer | ingested: 2026-08-24 | sha256: e76a43328989f6f8a87a4299f0cbcf80120d985097a95863eba7cec2cf74fc1c

### Machine endpoints
- Knowledge graph: https://pyweb.dev/api/graph.json
- Graph analysis: https://pyweb.dev/api/graph-analysis.json
- Context index: https://pyweb.dev/llms.txt