Computing Life · Share · YageAug 13, 2026, 08:00 UTC+8

DeepSeek open-sources DSH: agent loop as a hot-swappable plugin, paving the way for self-evolving agents

深度剖析 DeepSeek 最新的 Harness DSH：为了自进化这盘醋包了一整盘饺子

DeepSeek released its first agent harness, DSH, as open source on August 13. Unlike Codex or Claude Code, DSH treats the agent loop itself as a plugin that can be swapped at runtime. The Cordis runtime handles hot reloads, dependency notifications, and transactional rollbacks. For everyday coding, declarative plugins plus a quick restart are enough—DSH's imperative model adds complexity. But if you want an agent that can generate new tools or replace its own control flow mid-run, DSH is the only option with the infrastructure in place. The post does not disclose performance benchmarks or production-scale data.

Why it matters: DSH makes the agent loop itself a hot-swappable plugin — a real architectural difference, not marketing. But this is a third-party analysis, not an official launch, and DSH has zero production track record yet. Defaulted to the lower band per policy.

Read the original ↗Export Markdown

Take

This one's worth opening because DeepSeek finally open-sourced its agent harness, and the architecture is genuinely different from Codex or Claude Code. The core agent loop—the logic that decides how the model thinks, calls tools, and iterates—is a plugin you can swap at runtime. In every other harness, that logic is hardcoded and untouchable.

To support this, DSH ships with a runtime called Cordis that handles side-effect cleanup, dependency notifications, and transactional rollbacks during hot swaps. A single file, fiber.ts, runs 750 lines—you can see they've hit real concurrency and rollback edge cases, not just paper abstractions.

But I'll be real: for most daily coding, this is overkill. Codex's declarative plugins are dead simple—edit a config, restart in two seconds, done. DSH forces you into a heavier model where every plugin registers side effects, declares dependencies, and returns teardown functions. You just don't need in-process hot-swapping for search or skill plugins.

The useful bit is self-evolution. If an agent can generate new tools or even a new control loop mid-run, DSH is the only harness with the infrastructure in place. Model capability is right at the edge too—generating a 50-line tool is routine, and a few-hundred-line agent loop is within reach of top models. Codex's loop is compiled into Rust with no slot to swap it. DSH provides that physical interface.

The post doesn't include performance benchmarks or production data—it's architecture analysis and source-code reading. I'd treat this as infrastructure for self-evolving agents, not something that'll speed up your daily coding.

Source: Computing Life · Share · Yage · yage.ai
Published: Aug 13, 2026, 08:00 UTC+8 · Aug 13, 2026