# dsh-bring-local-llm

> 让本地 LLM(Ollama/KoboldCpp/LM Studio/任意 OpenAI 兼容端点)接入 DeepSeek Harness，本地优先处理一部分信息，难点交给云端主模型：省在线 token、用上本地冗余算力。

## Metadata

- Author: [@Hed1an](https://github.com/Hed1an)
- Repo: <https://github.com/Hed1an/dsh-bring-local-llm>
- GitHub: [Hed1an/dsh-bring-local-llm](https://github.com/Hed1an/dsh-bring-local-llm)
- Stars: 0
- Language: JavaScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `deepseek-harness`, `dsh`, `dsh-plugin`, `koboldcpp`, `llamacpp`, `lmstudio`, `local-llm`, `offline`, `ollama`, `token-saving`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-15T09:17:05.000Z
- Added: 2026-08-15T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add github:Hed1an/dsh-bring-local-llm
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-bring-local-llm](https://deepseek-plugin.org/plugins/Hed1an/dsh-bring-local-llm)