dsh-llm-api-integration
Run the following command in DeepSeek Harness:
dsh plugin install satan9394/dsh-llm-api-integration
Paste the following prompt into your AI chat to install this plugin:
Install the plugin in DeepSeek Harness by running dsh plugin install satan9394/dsh-llm-api-integration; source code is available at https://github.com/satan9394/dsh-llm-api-integration
About this plugin
dsh-llm-api-integration is a model-inference plugin for DeepSeek Harness, focused on simplifying LLM API integration into a single plugin-level configuration. For developers who need to call external large-language-model endpoints within the Harness framework but want to avoid scattering low-level request logic across business code, it offers a cleaner onboarding path.
The plugin sits squarely in the model-inference layer: it wraps LLM API calls inside an independent plugin lifecycle so that callers can focus on inference results rather than repeatedly handling authentication, endpoint routing, and other plumbing. It is open-sourced under the MIT license and can be freely vendored into any project.
It is best suited for teams that need to wire one or more LLM inference endpoints into DeepSeek Harness quickly, want to manage API integration as a first-class plugin concern, or simply value clean code layering in their inference pipelines. If you are building a Harness-based reasoning workflow, it can serve as the foundational LLM API integration layer.
Use Cases
- Quickly wire external LLM inference endpoints into a Harness pipeline
- Manage API auth and endpoint routing as a unified plugin layer
- Build a reasoning service with a clean LLM integration layer
Best For
- Developers calling LLM endpoints within DeepSeek Harness
- Teams building inference pipelines with clean layering
- Projects looking to eliminate repeated request boilerplate
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.