能力标签

🔌 MCP 🤖 Agent 🔄 工作流 🌐 翻译 💻 CLI 🔗 REST API 🧬 Embedding 🖼 视觉 🔊 TTS 🎙 STT

⚙️

Agent工作流

MLX工作室

无代码搭建完整 AI 自动化流程

英文名：mlxstudio

⭐ 767 Stars 🍴 49 Forks 📄 未公布协议 🏷 AI 8.0分

8.0AI 综合评分

aiai-agentsanthropic

⚙️ 配置说明 🔍 查看原项目

✦ AI Skill Hub 推荐

经 AI Skill Hub 精选评估，MLX工作室获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 8.0 分，适合有一定技术背景的用户使用。

📚 深度解析

MLX工作室是一套完整的 AI Agent 自动化工作流方案。随着 AI 能力的不断提升，基于 Agent 的自动化工作流正在成为提升个人和团队效率的核心方式。区别于传统的 RPA 自动化（模拟鼠标键盘操作），AI Agent 工作流通过理解任务意图、动态规划执行路径，能够处理更复杂的非结构化任务。

MLX工作室工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。

在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 8.0 分，是同类 Agent 工作流中的精选推荐。

📋 工具概览

MLX工作室是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。

GitHub Stars

⭐ 767

开发语言

多语言

支持平台

Windows / macOS / Linux

维护状态

正常维护，社区驱动

开源协议

未公布

AI 综合评分

8.0 分

工具类型

Agent工作流

Forks

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

📌 核心特色

可视化 Agent 工作流编排，无需编写复杂代码
支持多步骤自动化任务链，实现全流程无人值守
与外部 API、数据库和第三方服务无缝集成
内置错误处理与自动重试机制，保障稳定运行
提供可复用的自动化模板，快速在同类场景部署

🎯 主要使用场景

自动化日常重复性工作，将精力集中于创造性任务
构建数据采集 → 处理 → 输出的完整自动化管线
实现跨平台、跨系统的数据流转和业务协同

以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。

安装命令

# 克隆仓库
git clone https://github.com/jjang-ai/mlxstudio
cd mlxstudio

# 查看安装说明
cat README.md

# 按 README 完成环境依赖安装后即可使用

📋 安装步骤说明

访问 GitHub 仓库获取工作流文件
在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
上传工作流文件
按照提示配置必要的环境变量和 API Key
运行测试确认流程正常后投入使用

以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。

常用命令 / 代码示例

# 查看帮助
mlxstudio --help

# 基本运行
mlxstudio [options] <input>

# 详细使用说明请查阅文档
# https://github.com/jjang-ai/mlxstudio

以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。

配置示例

# mlxstudio 配置说明
# 查看配置选项
mlxstudio --config-example > config.yml

# 常见配置项
# output_dir: ./output
# log_level: info
# workers: 4

# 环境变量（覆盖配置文件）
export MLXSTUDIO_CONFIG="/path/to/config.yml"

📑 README 深度解析真实文档完整度 87/100 查看 GitHub 原文 →

以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

简介

The native macOS desktop app for local AI on Apple Silicon

vMLX v2 — native Swift + Metal, 50–95 t/s on M-series. Zero PyTorch in the hot path. Pure SwiftUI. Drag and drop models. The Python panel above remains available for legacy support.

<a href="#features">Features</a> • <a href="#screenshots">Screenshots</a> • <a href="#api-server">API Server</a> • <a href="#image-generation">Image Generation</a> • <a href="#advanced-quantization">JANG Quantization</a> • <a href="#system-requirements">Requirements</a> • <a href="#build-from-source">Build</a> • <a href="#한국어-korean">한국어</a>

---

MLX Studio is a complete desktop app for running LLMs, VLMs, and image generation models locally on your Mac. No cloud, no API keys, no data leaving your machine. Supports every model on mlx-community -- Qwen, Llama, Mistral, Gemma, Phi, DeepSeek, and thousands more. Built on vMLX Engine and Apple's MLX framework.

JANG 2-bit destroys MLX 4-bit on MiniMax M2.5: | Quantization | MMLU (200q) | Size | |---|---|---| | JANG\_2L (2-bit) | 74% | 89 GB | | MLX 4-bit | 26.5% | 120 GB | | MLX 3-bit | 24.5% | 93 GB | | MLX 2-bit | 25% | 68 GB | Adaptive mixed-precision quantization keeps critical layers at higher precision while compressing the rest. Check scores at jangq.ai. Models at JANGQ-AI.

---

Features

System Requirements

Requirement	Minimum
macOS	14.0 Sonoma or later
Chip	Apple Silicon (M1 / M2 / M3 / M4)
RAM	8 GB (16 GB+ recommended for larger models)
Disk	~500 MB for app; models range from 1-50 GB each

---

Install

Option 2: CLI via pip (Engine Only)

The vMLX inference engine is published on PyPI as vmlx -- same engine that powers the desktop app, available as a standalone CLI. This is real, published software with 1,894+ tests.

```bash

Or with pip in a virtual environment

python3 -m venv ~/.vmlx-env && source ~/.vmlx-env/bin/activate pip install vmlx vmlx serve mlx-community/Qwen3-8B-4bit ```

Note: On macOS 14+, pip install vmlx without a venv will fail with "externally-managed-environment". Use uv, pipx, or create a venv first.

Once running, your local OpenAI-compatible API server is live at http://localhost:8000. Point any OpenAI or Anthropic SDK client at it.

---

Build from Source

```bash git clone https://github.com/jjang-ai/vmlx.git cd vmlx

Quick Start

Launch MLX Studio from Applications
Pick a model -- browse HuggingFace models in the Server tab, or enter a repo name (e.g., mlx-community/Qwen3-8B-4bit)
Start the session -- the model downloads automatically and the server starts
Chat -- switch to the Chat tab and start talking

That's it. The app manages the entire Python engine, model downloads, and server lifecycle for you.

---

Screenshots

Chat Interface Streaming conversations with thinking mode, code highlighting, and markdown	Agentic Coding Full tool calling with file I/O, shell execution, and web search
Image Generation & Editing Flux Schnell, Dev, Z-Image Turbo, Klein + Qwen Image Edit	Anthropic API Compatible Drop-in /v1/messages endpoint for Anthropic SDK clients
Developer Tools Convert, inspect, and diagnose models	Model Conversion GGUF to MLX, 16-bit to quantized, and JANG adaptive mixed-precision
HuggingFace Browser Search and download models directly in-app	Menu Bar Running models, GPU memory, and quick controls

---

Recommended: use uv (fast, no venv hassle)

brew install uv uv tool install vmlx vmlx serve mlx-community/Qwen3-8B-4bit

OpenAI-Compatible API Server

Every session launches a full API server. Point any OpenAI SDK client at your local endpoint:

POST /v1/chat/completions -- Chat Completions API with streaming, tool calling, vision, structured output
POST /v1/responses -- OpenAI Responses API (agentic format) with streaming
POST /v1/completions -- Text completions
POST /v1/images/generations -- Image generation (Flux/Z-Image models, OpenAI format with usage field)
POST /v1/images/edits -- Image editing (Qwen Image Edit, instruction-based)
POST /v1/embeddings -- Text embeddings with dimension control and batch processing
POST /v1/rerank -- Document reranking
POST /v1/audio/speech -- Text-to-speech (Kokoro TTS)
POST /v1/audio/transcriptions -- Speech-to-text (Whisper)
GET /v1/models -- List loaded models
GET /health -- Server health with VRAM usage, queue length, load times

Anthropic API Compatibility

Drop-in replacement for the Anthropic Claude API:

POST /v1/messages -- Anthropic Messages API format
Anthropic SDK tool calling format (auto-translated to internal format)
Vision/multimodal support via Anthropic content blocks
Use the Anthropic Python/TypeScript SDK -- just change the base_url to your local server
Copy-paste code snippets in the API tab for curl, Python, and JavaScript

Chat Interface

Full-featured conversation UI:

Persistent history -- SQLite (WAL mode) with full message, metrics, and tool call history
Markdown rendering -- GitHub-flavored markdown with syntax highlighting
Reasoning display -- collapsible thinking sections for reasoning models
Tool call display -- inline tool execution with status and results
Streaming metrics -- live tokens/second, time-to-first-token (TTFT), prompt processing speed, prefix cache hit rate
System prompts -- per-chat custom system message
Chat settings -- per-chat overrides for temperature, top-p, top-k, min-p, repetition penalty, max tokens, stop sequences
Chat folders -- hierarchical organization
Message search -- full-text search across chat history
Export/Import -- ShareGPT format
Voice chat -- STT + TTS integration

Tool Calling & Agentic Workflows (14 Parsers)

Auto-detected tool call parsers for every major model family:

Qwen (qwen3, qwen2.5) -- <tool_call> XML format
Llama 3 -- <function=name> format
Mistral -- [TOOL_CALLS] format
Hermes -- <tool_call> JSON format
DeepSeek -- function call blocks
GLM-4.7 -- GLM tool format
MiniMax -- MiniMax function calling
Nemotron -- NVIDIA Nemotron tool format
Granite -- IBM Granite format
Functionary -- Functionary v3 format
XLAM -- Salesforce xLAM format
Kimi -- Moonshot Kimi format
Step-3.5 -- StepFun format
Auto-detection from model_type in config.json with regex name fallback

26+ Built-in Tools: - File I/O -- read, write, edit, patch, copy, move, delete, create directory, list directory, file info, insert text, replace lines, directory tree - Search -- ripgrep file search with regex and glob, glob file finder, unified diff - Execution -- shell commands (60s timeout), background processes (5m auto-kill), process output polling - Web -- DuckDuckGo search, Brave Search API, URL fetch with HTML-to-text - Developer -- token counter, regex find-replace across files, git operations, clipboard read/write, diagnostics (TypeScript/ESLint/Python linting) - Interactive -- ask_user tool for human-in-the-loop interrupts - Per-category toggles: enable/disable file, search, shell, web tools independently - Auto-continue agent loops (up to 10 tool iterations per request) - MCP (Model Context Protocol) -- connect external tool servers, merge tool definitions, execute MCP tools via API