Pi extension for the ModelScope OpenAI-compatible provider

MCP Server providing vision capabilities for LLMs via GLM-4.6V, SiliconFlow, ModelScope, OpenAI, Claude, Gemini, and Coding Plan (Kimi K2.5)

n8n node for ModelScope API-Inference services including LLM, Vision, and Text-to-Image models

n8n node for ModelScope API-Inference services including LLM, Vision, and Text-to-Image models

Ultra-fast on-device ASR engine & CLI with FunASR verbatim transcripts, ModelScope auto-acceleration, Metal/GPU inference, and subtitle generator.

A tool that can automatically convert huggingface and modelscope spaces to free API.

MCP server for ModelScope API-Inference image generation with async task polling and LoRA model support

`@xpert-ai/plugin-modelscope` adds ModelScope Skills as a skill repository source provider for XpertAI.

ModelScope Text-to-Image MCP Server

Unified DeepSeek Harness connector: edit MCP servers (cordis.patch.yml), user skills (~/.dsh/skills) and browse the ModelScope MCP/Skills marketplaces from one Web UI settings page.

ModelScope text-to-image MCP server for Claude Desktop and other MCP clients

Reliable vision MCP server with ordered fallback across ModelScope, Zhipu, and OpenAI-compatible models

n8n community node for Modelscope Image generation API - Generate images using Modelscope AI models

Embedded local LLM provider for wasmagent — node-llama-cpp adapter with grammar-constrained tool calling, multi-mirror download (HF/hf-mirror/ModelScope), and cert pipeline

llama.cpp CLI tool - pure Node.js, no Python required. Download & run GGUF models from HuggingFace, ModelScope, or Ollama Registry. One-command setup for llama.cpp binaries.

Default configuration for claude-code-router with ModelScope support

pi (AI coding agent CLI) extension for mainland-China users: curated access to free-first model providers including OpenCode Zen, SenseNova, SiliconFlow, ModelScope, NVIDIA NIM, Cloudflare, and Agnes AI. Providers support Pi-managed auth.json credentials

Alibaba DashScope (ModelScope) provider for Oh My Pi — Qwen3, GLM-5, Minimax M2.5, Kimi K2.5 via OpenAI-compatible coding API

Native vision for text-only pi models (DeepSeek, Llama, ...). Capability-aware chat attachment interception + vision-describe/vision-ask tools via any OpenAI-compatible vision endpoint (ModelScope, SiliconFlow, OpenRouter, GLM, Ollama), with intent detect

pi plugin for zvec-grep (zg): hybrid BM25 + embedding search and managed ripgrep in one tool, with freshness-guaranteed queries, CPU-pinned local embeddings, readiness commands, and a ModelScope mirror warm-up that works without access to huggingface.co