vmlx

48/100

⭐ 548 stars 🔀 66 forks 🔧 Python 📄 Apache-2.0 🕐 2026-05-24

🤖 AI/MLanthropic-apikvcache-compressionkvcache-optimizationkvcache-reusellmlmstudiomacbookmcp-server

vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!

📊 Score Breakdown

Recency10/20

Documentation7/15

Tests5/10

Auth/Security5/10

Star Velocity7/15

Security Audit7/15

Install Docs7/15

Language: Python

⚡ Install

# Clone and install
git clone https://github.com/jjang-ai/vmlx
cd vmlx
npm install  # or: pip install -r requirements.txt

View on GitHub → 📖 README 🐛 Issues Browse All Servers

🔗 Related MCP Servers

mcp-use

72/100 · B

Auto-claude-code-research-in-sleep

📬 Get weekly MCP server picks → Subscribe to Newsletter

About vmlx — vmlx is a 🤖 AI/ML MCP server with a quality score of 48/100 (D grade). It has ⭐548 GitHub stars, 🔀66 forks, and is written in Python. vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!

Browse 891 verified MCP servers across 8 categories. Filter by grade, search by keyword, and compare servers side-by-side on the leaderboard.