rapid-mlx-dsh-provider

Plugins in this repository

• @raullenchai/dsh-providerv0.3.0✓

  Native Rapid-MLX provider for DeepSeek Harness — teaches DSH what the local server already knows (memory-fitted context via max_model_len), plus model-management tools and a /rapid-mlx overview.

  homepage

  https://github.com/raullenchai/rapid-mlx-dsh-provider#readme ↗

  package.json

  package.json

  dsh.bundle.patch

  cordis.patch.yml

  Official core packages (6)

  • @deepseek-ai/cordis^4.0.1shared
  • @deepseek-ai/dsh-commands^0.1.0-rc.8shared
  • @deepseek-ai/dsh-llm^0.1.0-rc.8shared
  • @deepseek-ai/dsh-subprocess^0.1.0-rc.8shared
  • @deepseek-ai/dsh-tools^0.1.0-rc.8shared
  • @deepseek-ai/schemastery^3.18.1shared

Paths are pinned to commit 88f98e783598

Overview

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Required permissions

• No permission declaration is available. Review the source before installing.