mlx-serve — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by ddalcu · Agent Tool · ★ 1.3k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is mlx-serve safe to install? View the security audit →

About mlx-serve

mlx-serve — run any LLM on your Mac OpenAI- and Anthropic-compatible local inference for Apple Silicon — MLX and GGUF — faster than LM Studio on the same file. No Python. No cloud. No Electron. ddalcu.github.io/mlx-serve · Download MLX Core.app · Changelog ★ If mlx-serve saves you from spinning up another Electron app, star the repo — it genuinely helps people fin

agentanthropic-apiapple-siliconclaude-codedeepseek-v4diffusionggufimage-generationinferencellm

Quick Facts

Stars1,259
Forks115
LanguageZig
CategoryAgent Tool
Quality Score71.1837400706557/100
Open Issues44
Last Updated2026-09-14
Created2026-02-17
Platformsclaude-code
Est. Tokens~23k

mlx-serve alternative? Top 6 similar tools

Looking for a mlx-serve alternative? If you're comparing mlx-serve with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Rapid-MLX by raullenchai · ⭐ 3.7k

    The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling.

  • vllm-mlx by waybarrios · ⭐ 1.6k

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou

  • claude-code-local by nicedreamzapp · ⭐ 3.3k

    Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters inc

  • maclocal-api by scouzi1966 · ⭐ 341

    'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation and MLX Models and othe

  • axonhub by looplj · ⭐ 5.2k

    ⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & e

  • ruby_llm by crmne · ⭐ 4.4k

    The Ruby-native AI framework. Chats, agents, tools, images, audio, and video through one consistent API, in pl

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Zig Agent Tools

Frequently Asked Questions

What is mlx-serve?

mlx-serve is Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.. It is categorized as a Agent Tool with 1.3k GitHub stars.

What programming language is mlx-serve written in?

mlx-serve is primarily written in Zig. It covers topics such as agent, anthropic-api, apple-silicon.

How do I install or use mlx-serve?

You can find installation instructions and usage details in the mlx-serve GitHub repository at github.com/ddalcu/mlx-serve. The project has 1.3k stars and 115 forks, indicating an active community.

What are the best alternatives to mlx-serve?

The top alternatives to mlx-serve on Agent Skills Hub include Rapid-MLX, vllm-mlx, claude-code-local. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools