Artificial Intelligence · 17.08.2026, 10:25 UTC
DeepSeek AI Releases DeepSeek Harness in Developer Preview: An MIT-Licensed Agent Harness Where Everything is a Plugin
| Schweregrad | info |
|---|---|
| Kategorie | Artificial Intelligence |
| Quelle | MarkTechPost ↗ |
| Veröffentlicht | 17.08.2026 UTC |
Sicherheitsmeldung mit Schweregrad noch nicht bewertet. Technische Details im Tab „Originaltext“; empfohlene Schritte in der Checkliste.
DeepSeek released DeepSeek Harness v0.1 in developer preview and published the full source code under the MIT license. The project ships as dsh at deepseek-ai/deepseek-harness. A harness is the layer between a model and the environment it acts in — the tools, files, sandboxes, and control loop that let an agent keep working. DeepSeek frames it as Agent = Model + Harness. Most harnesses hard-code that layer: the agent loop, the tool registry, and the session store are fixed, and extension happens only at whatever hooks the authors exposed. Harness takes the opposite position, stated in the first lines of its README: everything is a plugin. Models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and the UI all sit behind Cordis plugin boundaries, and any of them can be selected, swapped, or extended in configuration without changing Harness source code. That makes this a kit for assembling agent runtimes rather than a fixed coding assistant, and it is why the release matters more than the model announcement it shipped alongside.
Is it deployable?
Yes, but as developer infrastructure, not as a production agent product. v0.1 is a developer preview.
Company level: AI-native startups and platform or developer-experience teams inside mid-to-large enterprises that already run internal tooling. Regulated enterprises can pilot it locally because it is MIT-licensed and self-hosted.
Industries: Software and devtools, financial services and insurance (auditable agent runs), healthcare and pharma R&D, cloud and semiconductor vendors publishing reference agent stacks, …