Tagged articles

reversible effects

2 articles · Page 1 of 1

Aug 14, 2026 · Fundamentals

How DeepSeek Harness Enables Agents to Rewrite Themselves at Runtime

The article analyzes DeepSeek Harness's plugin‑based architecture, its Cordis core for reversible side‑effects, the four operational modes—including a creation mode that lets agents dynamically add or remove components—and the underlying research paper that formalizes spatiotemporal composability for self‑modifying AI agents.

CordisDeepSeekHarness

0 likes · 16 min read

How DeepSeek Harness Enables Agents to Rewrite Themselves at Runtime

AI Engineering

Aug 13, 2026 · Artificial Intelligence

DeepSeek Harness Open‑Source: A Fully Pluggable AI Agent Framework Backed by a Formal Paper

The DeepSeek Harness SDK, now open‑source, offers a completely pluggable architecture for building AI agents, provides four preset modes, multiple entry points, a fail‑closed security model, and is underpinned by a rigorous academic paper on spatiotemporal composability that formalizes reversible effects and reactive coeffects.

AI AgentsCordisDeepSeek

0 likes · 18 min read

DeepSeek Harness Open‑Source: A Fully Pluggable AI Agent Framework Backed by a Formal Paper