Skip to content
View RaulMermans's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report RaulMermans

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
RaulMermans/README.md
Raúl Mermans — AI Engineer. Intelligence, Engineered. An animated constellation of connected systems. AI Engineer, Agent Infrastructure, Applied ML

Portfolio LinkedIn All repositories

About

I'm an AI Engineer building the infrastructure and products that turn intelligent models into usable systems. My work spans agent reliability, orchestration, local inference, applied machine learning, simulation, and decision intelligence.

I care about what happens beyond the demo: architecture, evaluation, operational boundaries, and whether the product solves a real problem.

Featured work

Reeprov ↗
Local-first debugging infrastructure for AI agents: capture, replay, causal comparison, evaluations, and regression gates.

Agent reliability · TypeScript + Python SDKs · Public beta
OpsTwin ↗
Decision lab comparing operational changes through paired, repeated simulation and uncertainty-aware evidence.

Next.js · FastAPI · SimPy · 430 reported passing tests · Live demo
BI Notebook Lab ↗
Browser-based DAX learning lab with an expression engine, semantic models, filter propagation, and executable grading.

TypeScript · 1,024 reported passing tests · 82/83 hand-verified DAX cases · Live demo
Relay ↗
A source-aware marketing analytics workspace for Meta Ads, Google Ads, and Shopify CSV exports.

Next.js · Data quality · 304 reported passing tests · Protected beta
Open VS Code Agent ↗
A coding-agent system optimized for a local 7B open-weight model, with strict tool boundaries and reproducible evaluation.

Ollama · Local inference · 37.5% → 75% success on a 24-task read-only benchmark · Public architecture edition
DemandOS ↗
Demand forecasting and inventory-risk planning with leakage-aware feature engineering, backtesting, and human-reviewed reorder proposals.

Python · Applied ML · Synthetic-data portfolio MVP · Live demo

Currently engineering

  • AAO / Applied AI Operations — a private, reusable foundation for governed AI workflows, execution, approvals, and adapter portability.
  • IRIS OS — an attention-first personal AI operating system with bounded specialist agents. The public repository documents the architecture; external side effects are not production-enabled.
  • HALO Control — a local AI control plane for workload orchestration and model routing. The public repository is an architecture edition, and AMD Halo hardware verification remains pending.

Other experiments: DataBrief AI · SearchSignal · Website Audit Agent · Overflow iOS

Technical stack

TypeScript, Python, React, Next.js, Node.js, FastAPI, PostgreSQL, SQLite, Docker, Git, GitHub Actions, Vercel

Agent orchestration · MCP · Local inference / Ollama · Evaluation harnesses · Playwright · Pytest · Vitest · SimPy · DAX

Open-source contributions

GitHub signals

GitHub activity summary (provided by a third-party statistics service)

Activity Signal — GitHub contributions


FROM MODELS TO OPERATIONAL SYSTEMS.

Pinned Loading

  1. Reeprov Reeprov Public

    Local-first debugging and reproducibility infrastructure for AI agents.

    TypeScript

  2. bi-notebook-lab bi-notebook-lab Public

    Browser-based analytical runtime for learning semantic models, DAX evaluation and filter context, with a conformance-tested expression engine.

    TypeScript

  3. Open-VS-Code-Agent Open-VS-Code-Agent Public

    Local coding agent designed and benchmarked for open-weight models, with explicit tools, verification and recoverable mutation.

    TypeScript

  4. IRIS-OS IRIS-OS Public

    Public architecture edition of a personal AI operating system: evidence-backed attention, governed agents, memory and recoverable execution.

    TypeScript

  5. AMD-HALO-Control AMD-HALO-Control Public

    Public architecture edition of a local AI control plane: model routing, telemetry, workload authorization and observability for AMD Halo.

    TypeScript

  6. OpsTwin OpsTwin Public

    Decision-support lab for testing service-workflow changes before deployment through paired discrete-event simulation, uncertainty analysis, and operational evidence.

    Python