About Grey Newell

Background

ML infrastructure engineer building evaluation, inference, and observability systems for AI. Creator of the MIST stack (MatchSpec, InferMux, SchemaFlux, TokenTrace), an eval and inference platform written in Go with zero external dependencies. Founding Engineer at Supermodel, building code analysis tooling for AI agents. Previously built distributed systems at Amazon and AWS. Published research on benchmarking Model Context Protocol servers.

Skills

Experience

Founder

2025 - Present
AgentLab (agentlab.us)

Founding Engineer

2025 - Present
Supermodel Tools

Graduate Student

2025 - Present
Georgia Institute of Technology

Education

Georgia Institute of Technology

2025 - 2028
Master of Science in Computer Science · Specialization: Machine Learning
Atlanta, GA

Mercer University

2010 - 2015
Master of Science in Engineering · Specialization: Computer Engineering
Macon, GA

Mercer University

2010 - 2015
Bachelor of Science in Engineering · Specialization: Computer Engineering
Macon, GA

Certifications

Industry Publications

Supermodel Engineering Blog

AWS Architecture Blog

AWS Training & Certification Blog

Projects

Route inference across LLM providers. Track cost per request.

89 Go Website

Eval framework. Define correct, test against it, get results.

22 Go Website

Ship evals before you ship features.

18 Markdown Website

Structured data compiler. Pass pipeline, pluggable backends.

12 Go Website

Serverless event-driven architecture for processing millions of daily events with near real-time visibility and strong resilience.

6 TypeScript

typescript-sdk supermodeltools

TypeScript SDK for Supermodel. Generate useful graphs of your codebase.

6 TypeScript

mcpbr supermodeltools

Benchmark runner for Model Context Protocol servers. Paired comparison experiments on SWE-bench.

6 Python Website

openapi-spec supermodeltools

OpenAPI spec for the Supermodel public API. Use as reference or generate your own clients.

5 YAML
AI

mcp supermodeltools

Supermodel MCP server. Generate code graphs in Cursor, Codex, or Claude Code.

5 TypeScript

arch-docs supermodeltools

GitHub Action to generate architecture documentation for any repository using Supermodel.

5 JavaScript
AI

Where did your tokens go? Spans, latency percentiles, alerts.

5 Go Website

dead-code-hunter supermodeltools

GitHub Action to find unreachable functions using Supermodel call graphs.

4 TypeScript

Shared core for the MIST stack. Zero external deps.

1 Go

supermodeltools.github.io supermodeltools

GitHub Pages site for Supermodel Tools.

Go
Go

Contact

Hit me up. I'm always down to collab.

Email

me at greynewell dot com

Social