One-click setup for Codex CLI and Claude Code. Supports Qwen, DeepSeek, Zhipu, Moonshot, SiliconFlow and custom APIs.

Simple prompt optimization MCP server with SiliconFlow API integration

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, AMD Radeon Cloud, Cloudflare, and Agnes AI. Providers support Pi-managed auth

Show your Claude Code subscription usage (5h / 7d, or balance) in the statusline. Supports Anthropic, Kimi, GLM, MiniMax, DeepSeek, StepFun, SiliconFlow, OpenRouter, Novita.

Unified real-time quota dashboard for DeepSeek Harness: OpenCodeGo windows, DeepSeek balance, OpenRouter credits, SiliconFlow and Moonshot balances in one collapsible panel — auto-detects configured credentials, no keys leave the host.

Multi-provider LLM adapter registry (OpenAI, Anthropic, Google, Azure, Amazon Bedrock, DeepSeek, Qwen, Kimi, MiniMax, GLM, SiliconFlow, Doubao, Grok, Ollama, and more) — extracted from OpenMAIC.

SiliconFlow CLI

SiliconFlow CLI Server

Voice input for the DeepSeek Harness (DSH) Web GUI: a microphone button in the chat composer that records audio, transcribes it through an OpenAI-compatible Whisper API (Groq / OpenAI / SiliconFlow), and inserts the recognized text into the input box.

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

Check all your AI subscription quotas in one command. Supports 17 platforms: OpenAI, Anthropic, Groq, Gemini, Zhipu, Z.ai, Google Cloud, Kimi, MiniMax, Abacus, Nano-GPT, Chutes, DeepSeek, OpenRouter, SiliconFlow, GitHub Copilot.

对接硅基流动实现画图

Multi-model vision understanding MCP server. Supports GLM-4.6V (Zhipu), DeepSeek-OCR (SiliconFlow - Free), Qwen3-VL-Flash (Aliyun), and Doubao-Seed-1.6 (Volcengine)

Switch between multiple API keys in the OpenCode TUI sidebar. Supports opencode-go, SiliconFlow, and any OpenAI-compatible provider.

koishi插件，支持openaiAPI格式的平台接入，如果你使用控制台将可以同时使用多个平台配置；支持分群组配置，为console界面深度优化，易于配置参数

Vision Bridge MCP Server — 让 DeepSeek（纯文本模型）通过 MCP 调用视觉模型来「看到」图片。支持 SiliconFlow / OpenAI 兼容 API，含图片压缩功能。

Zero-config AI code quality pipeline CLI: deterministic rule checks + AI review, 4-tier team-friendly scoring, HTML report, and a built-in SiliconFlow fallback. Review, auto-fix and generate tests from a single command.

Usage statistics plugin for the dsh web GUI: per-provider balance and coding-plan quota detection plus a live token usage ledger, with a dedicated pet bubble for the current provider

Thin wrapper around 20 free LLM APIs (OVHcloud, LLM7, Pollinations, Cerebras, Groq, NVIDIA NIM, OpenRouter, Google AI Studio, Cohere, GitHub Models, Cloudflare Workers AI, HuggingFace, Mistral, SambaNova, Z.AI, SiliconFlow, Aion Labs, Ollama Cloud, ModelS

Give text-only DeepSeek Harness models eyes: chat image attachments are described by a vision model before they reach the DeepSeek API. Works with any OpenAI-compatible vision endpoint (DashScope Qwen-VL, SiliconFlow, local MLX/Ollama, ...).