Plugins

Ollama provider for DeepSeek Harness with model management, health checks, rule-based local routing, and cloud fallback.

Connects existing IndexTTS 2.5 and GPT-SoVITS installations for sentence-level assistant reading in Harness web, with local process launch and playback controls.

Multi-language codebase intelligence for DeepSeek Harness and MCP-compatible IDEs: chat, search, audit, refactor, and board-ready reports from local code.

Use local MLX-LM or MLX-VLM models in DeepSeek Harness through a loopback OpenAI-compatible provider, with optional DSH-owned server startup.

Editable local and desktop dictation for DeepSeek Harness