dsh-llm-mlx
Use local MLX-LM or MLX-VLM models in DeepSeek Harness through a loopback OpenAI-compatible provider, with optional DSH-owned server startup.
通过回环 OpenAI-compatible 提供方在 DeepSeek Harness 中使用本机 MLX-LM 或 MLX-VLM 模型，并可选由 DSH 托管模型服务进程。
How to install
dsh plugin add github:robbywang25/dsh-llm-mlx About
dsh-llm-mlx 中文 Use a local MLX-LM or MLX-VLM model as a DeepSeek Harness provider. The plugin contributes a local-mlx model route through DSH's built-in OpenAI-compatible adapter and can optionally start and own mlx_lm.server or mlx_vlm.server for the lifetime of the DSH process. No model weights are included. Managed startup is limited to Apple-silicon macOS and binds the server to 127.0.0.1. The bundle also replaces DSH Desktop 2.0.3's macOS subprocess provider with the same upstream implementation loaded from the plugin dependency tree. This avoids a packaged node-pty path rewrite from app.…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-09-06
- Created
- 2026-08-25
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh-plugin, local-ai, mlx, mlx-lm
Related plugins
dsh-plugin-subscriptions
V1ki/dsh-plugin-subscriptions
Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.
dsh-workbuddy-connect
corrinehu/dsh-workbuddy-connect
Brings the models in the WorkBuddy desktop app straight into DeepSeek Harness — zero configuration in the DSH chat.
claude-code-router
musistudio/claude-code-router
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
dsh-thinking-effort
hytime/dsh-thinking-effort
Configure reasoning-effort levels and sub-agent defaults for custom DSH models.