Model Providers Plugins Model Providers

31 plugins

LLM adapters and local model connectors

31 plugins

Sort: Featured
  • Listed Bundle verified

    NewAPI (OpenAI-compatible gateway) LLM provider: registers a `newapi` route with chat-only model discovery, auto-fills model parameters (context window, reasoning effort) from models.dev, and adds a Web settings section for the base URL and API key.

    dsh plugin --profile default add github:wenzetan/dsh-llm-newapi
  • Listed Bundle verified

    Global Simplified-Chinese mode: a 中 switch in the input box that injects language requirements (Chinese or English per region) into every session's system prompt; anchored mode forces English thinking for anchored presets.

    dsh plugin --profile default add github:dawnliming/dsh-chinese-mode
  • Listed Bundle verified

    Codex App Server model provider using a local Codex login, with session reuse, Harness tool bridging, native action traces, and durable generated-image projection.

    dsh plugin --profile default add github:wss534857356/dsh-plugin-codex
  • Listed Bundle verified

    Simulates a Codex environment for selected model routes to improve GPT-family model tool-call success.

    dsh plugin --profile default add github:OpenTritium/dsh-codex-shim
  • Listed Bundle verified

    Use third-party subscription accounts in DeepSeek Harness: chat, image understanding, image generation, and image editing with the models your subscription covers, with available models and reasoning levels synced from your account; currently supports OpenAI/ChatGPT subscriptions, more providers planned.

    dsh plugin --profile default add github:kinoward/dsh-plugin-subhub
  • Listed Bundle verified

    Qwen multi-modal plugin support.

    dsh plugin --profile default add github:omdsh-dev/Qwen-MM-Plugins

Frequently Asked QuestionsFAQ

LLM adapters and local model connectors