rdmsm4x-changelog-20260830-0030-apple-mlx-suite-and-mcp-integration

Summary

Created canonical apple-mlx project at ~/dev/apps/apple-mlx, built automated Apple Silicon installer and fleet deployment automation, implemented Model Context Protocol (MCP) server mlx-mcp with JSON-RPC 2.0 stdio, configured LaunchAgent daemon, and published comprehensive LLM runtime ranking (Ollama vs MLX vs LM Studio vs Apple Foundation Models).

Details of Changes

1. New Canonical Project: ~/dev/apps/apple-mlx

• Location: rdmsm4x:~/dev/apps/apple-mlx/ (Git repository initialized on main).
• Core Binaries:
  • bin/mlx-mcp & bin/mlx_mcp_server.py: Native stdio Model Context Protocol (MCP) server exposing mlx_generate, mlx_chat, mlx_list_models, mlx_load_model, and mlx_metal_status.
  • bin/mlx-server: OpenAI-compatible HTTP server (/v1/chat/completions) wrapping mlx_lm.server with Metal GPU acceleration on port 8080.
  • bin/mlx-cli: Fast interactive/non-interactive CLI text generation.
  • Symlinked to ~/bin/mlx-mcp, ~/bin/mlx-server, and ~/bin/mlx-cli.

2. Fleet Installation & Deployment Automation

• scripts/install_mlx.zsh: Dynamic Homebrew detection (brew --prefix), uv virtual environment creation (~/.local/share/mlx-env), package installation (mlx==0.32.2, mlx-lm==0.31.3, mlx-whisper, fastapi, uvicorn), Metal verification, and MCP schema registration.
• scripts/fleet_deploy_mlx.zsh: Multi-host deployment orchestrator across all 6 fleet machines (rdmsm4x, rdmbair15m5, rdmbair13m5, jdmbair13m5, rdmpw3265m, rdmpw3275m) over Tailscale SSH.
• launchd/com.eastcoastscience.mlx.plist: Native macOS LaunchAgent for persistent background model serving.

3. Comprehensive LLM Runtime Comparison

• Published docs/LLM_RUNTIME_COMPARISON.md:
  • Rank 1: Apple MLX (mlx-lm) — optimal memory bandwidth (94-98%), zero-copy unified memory, fastest TTFT and highest decode tokens/sec.
  • Rank 2: Ollama — best for multi-node fleet CLI ergonomics and rapid model pulling.
  • Rank 3: omlx — MLX Metal speed with Ollama REST API compatibility.
  • Rank 4: llama.cpp — bare-metal C++ GGUF inference.
  • Rank 5: LM Studio — interactive desktop GUI testing.
  • Apple Official Releases: Documented Apple ML Research releases (MLX, OpenELM, Ferret-v2, Depth Pro, MobileCLIP, mlx-community) vs on-device Apple Intelligence Foundation Models (AFM-on-Device 3B CoreML model).

4. Verification & Testing

• Unit test suite tests/test_mlx_mcp.py executed: 4/4 tests passed (0.16s).
• Verified Metal GPU compute on rdmsm4x: Device(gpu, 0) initialized, zero-copy arrays evaluated.
• Verified MCP stdio handshake, tools listing, and mlx_metal_status tool calls.
• Resolved fleet ticket FEAT-20260830-40.