unipds-engenharia-de-ia-aplicada/engenharia-de-software-com-ia-aplicada

Códigos e referências usados na Pós de Engenharia de Software com IA Aplicada

What it solves

This project provides a comprehensive curriculum and practical codebase for software engineers looking to integrate Artificial Intelligence into their development workflows, operations, and application architecture.

How it works

The repository is organized into modular learning paths. Each module contains theoretical foundations followed by hands-on projects. It covers everything from basic machine learning and prompt engineering to advanced topics like RAG (Retrieval-Augmented Generation), autonomous agent creation using LangGraph, and AI-driven infrastructure operations (AIOps) using tools like CrewAI and Kubernetes.

Who it’s for

It is designed for software developers and engineers who want to move beyond using AI as a simple chatbot and start building, deploying, and governing AI-powered systems and autonomous agents.

Highlights

  • Practical labs covering Web AI, including running models directly in the browser.
  • Deep dives into agentic workflows, including ReAct patterns, memory management, and multi-agent systems.
  • Extensive coverage of AI-Ops, including IaC generation, Kubernetes troubleshooting, and FinOps.
  • Integration guides for modern tools like MCP (Model Context Protocol), LangChain, Ollama, and Groq.
  • Real-world project examples, such as the 'OpsPilot' incident commander agent.

Related

  • Project
    kantord/SeaGOAT

    SeaGOAT is a local, AI‑augmented code‑search engine that indexes a repository with vector embeddings (via ChromaDB) and lets you query it using natural language or regex, running entirely on your machine.

  • Project
    huggingface/llm-vscode

    A VS Code extension that provides AI-powered ghost-text code completion and code attribution using various LLM backends like Hugging Face and Ollama.

  • Project
    griffinmartin/opencode-claude-auth

    A plugin for OpenCode 2 that enables authentication via existing Claude Code subscription credentials, removing the need for separate API keys.

  • Project
    2akouwu/reverify

    Reverify is a Python toolkit that lets LLMs propose facts about binaries (or source code) and then deterministically checks those claims against the actual file. It offers pure‑Python parsers/disassemblers plus optional native back‑ends (Capstone, Unicorn, LIEF, Z3, angr). Verified facts are stored in a ledger, enabling AI agents to roll over contexts without losing trustworthy state. The tool is packaged on PyPI, includes a CLI and an MCP server for agent integration, and has been benchmarked to catch 100 % of hallucinated claims on real Windows binaries.