anybody i know using claude code to run lots of ML?

@withneo just launched an AI/ML expert as an MCP server that can help run these cheaper and faster.

link: https://t.co/DjFqHMRv9f

ping @saurabhvij137 to learn more https://t.co/QbiwgIysqt

Claude Code + NEO: Ship production AI from your terminal

Source: https://heyneo.com/claude-code

Ship production AI directly insideClaude Code

Install neo-mcp

Add NEO’s MCP server to any environment withPython 3.11+.

Terminal

pip install neo-mcp

Create your Secret Key

Open your NEO dashboard, create a key, and copy it. Keys look likesk-v1-….

Get Access Key

Connect Claude Code

Register NEO with one command, then just ask in a new chat to ship work.

Command

claude mcp add --scope user neo \
  -e NEO_SECRET_KEY=sk-v1-your-key \
  -- python3 -m neo_mcp

Using Cursor, VS Code, or another MCP client?See the neo-mcp setup.

Just describe it. NEO ships it.

Independent benchmark

62% cheaper. Better answer.

The task: benchmark a speech-to-text model on a CPU-only Azure VM — 2 cores, 7.7 GB RAM, no GPU. Claude Code alone reached for the obvious HuggingFace + PyTorch path and iterated in real time. NEO spent two minutes researching first, then chose ONNX Runtime for its AVX2-optimized CPU kernels — same task, same machine.

Cost per task

1\.960.74

62% cheaper

Runtime (RTF)

0.5190.328

37% faster

Backend chosen

PyTorchONNX Runtime

CPU-optimized

Benchmark by Gaurav Vij ·Read the full writeup

Start shipping.

Install once, then delegate ML work to NEO from any Claude Code session.

Neo is a fully autonomous AI Engineer capable of building AI apps, agents, performing experiments, evals, optimizations across your AI products and ML models.