vesta-mac-dist

概述

Vesta 是专为 Apple Silicon Mac 设计的综合 AI 聊天应用，具有强大的 MCP 服务器实现。该应用同时支持五种不同的 AI 后端：Apple Intelligence、MLX、llama.cpp、HuggingFace Inference API 和 OpenAI 兼容 API 服务器。其 MCP 服务器提供 41+ 工具用于后端管理、聊天操作、模型处理、视觉分析和系统诊断，以及 6 个资源和 7 个提示。服务器通过令牌身份验证在 TCP 回环上运行，并与 Claude Code 集成以实现应用程序的代理控制。

试试问 AI

装完之后，这里有 5 个你可以让 AI 做的事：

• backend_management

  Manage AI backends (Apple Intelligence, MLX, llama.cpp, HuggingFace, External AI)

  试试:Switch to MLX backend试试:Configure OpenAI-compatible API server
• model_download

  Download AI models from HuggingFace or other sources

  试试:Download Qwen3-VL model试试:Get latest Gemma 4 model
• vision_analysis

  Analyze images using vision-language models

  试试:Describe this image试试:What objects are in this screenshot?
• conversation_search

  Search conversation history with SQL queries or full-text search

  试试:Find our discussion about macOS security试试:Show me all messages with MLX backend
• image_generation

  Generate images using FLUX or Stable Diffusion models

  试试:Create a sunset over mountains image试试:Generate a portrait of a cyberpunk city
• video_generation

  Generate videos from text prompts using text-to-video models

  试试:Create a 10-second video of ocean waves试试:Generate an animation of a growing tree
• speech_to_text

  Transcribe audio to text using Whisper models

  试试:Transcribe this meeting recording试试:Convert voice memo to text
• text_to_speech

  Convert text to speech using Kokoro or Marvis TTS models

  试试:Read this article aloud试试:Generate voice from my text
• model_management

  Load, unload, and manage AI models in memory

  试试:Unload Qwen3-VL model试试:Check which models are currently loaded
• diagnostics

  Run diagnostic checks on the app and models

  试试:Check system resources试试:Test model loading performance
• ui_navigation

  Navigate and control the application UI

  试试:Switch to settings panel试试:Open conversation history view
• app_settings

  Configure application settings and backend parameters

  试试:Change MLX context size试试:Configure HuggingFace API key

可对比工具

安装

brew tap scouzi1966/afm
brew install --cask scouzi1966/afm/vesta-mac

{
  "mcpServers": {
    "vesta": {
      "command": "nc",
      "args": ["localhost", "1337"],
      "env": {"VESTA_MCP_TOKEN": "your_token_here"}
    }
  }
}

FAQ

Vesta 支持 AI 什么模型？

Vesta 支持 5 个后端：Apple Intelligence、MLX、llama.cpp、HuggingFace Inference API 和 OpenAI 兼容 API 服务器。

如何在 Vesta 中启用 MCP 服务器？

MCP 服务器在 Vesta 运行时自动启用。在 Claude Desktop 中配置本地连接详细信息即可。

vesta-mac-dist 对比