Ian Greenberg

Ian Greenberg

I build marketing operations and GTM systems: campaign platforms, CRM integrations and AI-assisted business workflows.

Marketing operationsCRM automationApplied AI
01

Work

Selected business systems and research.

SIG / SIG University

Marketing Manager

Built and deployed a campaign operations platform connecting Salesforce/Pardot, Cvent, Stripo and Smartsheet. The platform supports campaign work, reporting and AI-assisted retrieval over campaign and content data.

July 2024 - April 2026

See the marketing operations work

Open source

vLLM — PR #46218

A dtype bug in the AWQ/GPTQ path for MLA attention. Inference engines are where a single wrong assumption costs everyone throughput, so the fix is small and the reading was not.

Submitted June 2026; closed unmerged August 2026
Z-School

Director of AI Systems & Automations

Built MCP integrations connecting Zoho CRM, Calendly and WorkDrive, scheduled leadership reporting, and agent workflows with approval controls. Company leadership attributed $75K in revenue to the customer-reactivation work.

April - June 2026; selected work also spans prior consulting
Cortex

Automated course creation

Co-built software that turns source material into structured university courses. Deployed at roughly twenty universities through Z-School's partner network.

with Gogentic.ai
Gogentic.ai

Marketing and AI Automation Consultant

The practice the Z-School and Cortex work was built through. Also where the internal tooling lives — automated financial reporting, marketing systems, and the harnesses the projects below came out of.

February 2025 - present; began alongside SIG employment
Research

SMU — Center of Creative Computation

Affiliated researcher. Cluster and DGX SuperPOD allocation through 2027, used for inference work on large models — speculative decoding, quantisation, and what actually holds up at long context.

independent · through 2027

Before this I spent three years running a company I co-founded — one food truck in Lubbock that became three concurrent locations and 30+ employees. Payroll depending on you is why I care whether an agent's action is reversible.

02

Projects

Each links to a technical write-up.

GPU Cats macOS · C++

Coding agents get animated bodies on an island you can watch. Underneath: a real orchestration pipeline in isolated git worktrees, local Whisper and Kokoro for voice, persistent memory across sessions.

Visit →
realconnectorC++ · Qt6

Remote-desktop control built around Moonlight, Sunshine and Tailscale — an operator console for machines, not screen sharing.

Read →
localnpc-engineRust

A harness for running local models on real tasks: tools, replayable traces, evals, and a gate that verifies before it lets a run finish.

Read →
localbrowserPython · Docker

Self-hosted web search and page reading for local agents. No API keys, no per-query bill, and a quarantined model between the open web and the one holding your tools.

Read →
npcagentPython

Turns a sentence into a durable run in a local repo — by driving the coding CLI you already have, inside tmux, and handing it tools back over MCP.

Read →
daedalusTypeScript

Compiles a goal into a contract, freezes the evaluators behind a hash, and scores every attempt against them. Proof before progress.

Read →
assetfarmerPython

One keyed generation becomes registered sprite frames. An agent writes the choreography; deterministic code does the keying, slicing and sub-pixel registration.

Read →
codesearchPython

Tree-sitter chunking, embeddings and lexical search fused by reciprocal rank, then reranked. Built to answer questions about a codebase, not to grep it.

Read →
ian-operatorJavaScript · MCP

An operator kernel where the model proposes and code disposes. Every consequential action is graded against a policy lattice before anything executes; defaults are refusals.

Read →
ian-brainTypeScript · MCP

A folder of markdown read as a graph. Vector, keyword and neighbour retrieval behind one router, so an agent pulls the relevant subgraph instead of the whole wiki.

Read →
alwaysPython · Rust

A self-hosted voice assistant that listens continuously — capture, transcription, barge-in and turn-taking, built so interruption feels like conversation rather than a race.

Read →
FutureMarketPython · React

An equities research system that logs every prediction with an entry price, reconciles it against what actually happened, and grades its own strategies on the result.

Visit →