Skip to content
View monkaS013's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report monkaS013

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. 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
monkaS013/README.md

Hi, I'm Vinicius Morais

AI & Automation Engineer. I'm an electrical engineer who moved into data and AI. The things I build end up in production. One of them is an internal HR platform that a whole company uses every day. Right now I'm building a microgrid simulator checked number by number against a commercial engineering tool.

Engenheiro de dados & IA. Construo sistemas de IA e automação que chegam a produção.

Featured

  • portfolio: index of my work, with open-source repos and sanitized case studies of production systems (EN + PT).
  • rag-docs: offline-first RAG. A LangGraph pipeline over pgvector, with five OWASP-LLM guardrails and a precision@k eval.
  • brasilapi-mcp: an MCP server I wrote from scratch, exposing the public BrasilAPI as eight tools.
  • multi-llm-ensemble-extractor: three LLM providers read the same document in parallel, and each field is consolidated by majority vote.
  • nl2sql-ecommerce-agent: ask in plain language, and it computes the number in a sandbox and shows you the code behind it.
  • doc-analyzer-evals: structured document extraction with a gold-standard evaluation harness.

Stack

Python · RAG · pgvector · LangGraph · agents · MCP · evals · FastAPI · Next.js · DuckDB · SQL · Power BI

Contact

LinkedIn · vinicius_morais99@hotmail.com

Pinned Loading

  1. doc-analyzer-evals doc-analyzer-evals Public

    Structured document extraction with a gold-standard evaluation harness (precision / recall / F1).

    Python

  2. nl2sql-ecommerce-agent nl2sql-ecommerce-agent Public

    Natural-language-to-SQL agent over the Olist e-commerce dataset, with a SQL safety layer and a self-repair loop.

    Python

  3. portfolio portfolio Public

    AI & Automation Engineer portfolio - open-source projects and sanitized case studies of production systems (EN + PT).

  4. claude-usage-monitor claude-usage-monitor Public

    Floating Windows widget showing real Claude plan usage (5h session and week) - zero network, zero tokens.

    Python 1