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 raullenchai · Codex Skill · ★ 3.9k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Rapid-MLX safe to install? View the security audit →
Rapid-MLX Run AI on your Mac. Faster than anything else. Run local AI models on your Mac — no cloud, no API costs. Works with Cursor, Claude Code, and any OpenAI-compatible app. pip install → serve Gemma 4 26B → chat + tool calling → works with PydanticAI, LangChain, Aider, and more. Speed (
| Stars | 3,891 |
| Forks | 426 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 67.262934157063/100 |
| Open Issues | 45 |
| Last Updated | 2026-10-03 |
| Created | 2026-02-25 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~22k |
These tools work well together with Rapid-MLX for enhanced workflows:
Looking for a Rapid-MLX alternative? If you're comparing Rapid-MLX with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swif
Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters inc
vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NP
LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing,
Explore other popular codex skill tools:
Rapid-MLX is Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server and Mac app for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Release-. It is categorized as a Codex Skill with 3.9k GitHub stars.
Rapid-MLX is primarily written in Python. It covers topics such as anthropic-api, apple-silicon, claude-code.
You can find installation instructions and usage details in the Rapid-MLX GitHub repository at github.com/raullenchai/Rapid-MLX. The project has 3.9k stars and 426 forks, indicating an active community.
The top alternatives to Rapid-MLX on Agent Skills Hub include vllm-mlx, mlx-serve, 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.
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: