Runnable AI engineering modules: agents, MCP, memory, retrieval, voice, fine-tuning, MLOps, and security. Each folder is one module with its own README.
Reading about AI engineering only goes so far. These modules run. You'll find:
- 19 modules in three tiers, from first scripts to full services
- Agents in LangGraph and the OpenAI Agents SDK, plus a 7-lesson MCP course
- Redis for memory and retrieval, and a Neo4j knowledge graph
- Deploys to AWS, GKE, and Kubernetes
- A live voice agent and an LLM-based code detector
Every module README lists what it is, how to run it, and what it needs.
Each module is self-contained. Open its README, copy the keys it names into a .env, and run the commands.
- New to this? Start with the Beginner modules, such as
redis-basicsandwebhooks. - Build agents. Move to Intermediate with
langgraph,openai-agents, andmcp-crash-course. - Go deeper. Try the Advanced modules: agentic RAG, Kafka pipelines, and Kubernetes.
- Know the tags.
Projectis a runnable app.Tutorialis a set of small scripts.Courseis an ordered series.Referenceis material to read.
Most Python modules use uv. Python 3.13 or newer, and a current Node.js LTS for the TypeScript modules.
Single ideas and small deploys. Start here.
- OpenAI Agents SDK in TypeScript 路
Tutorial- Hello world, agent as tool, and dynamic instructions.
- Redis basics 路
Tutorial- Redis strings and lists from Node.js and Python.
- Webhooks 路
Tutorial- An order notification system with FastAPI webhooks.
- FastAPI authentication 路
Project- Argon2 password hashing and bearer-token login.
- AWS EC2 with FastAPI 路
Tutorial- Deploy a FastAPI bookstore to an EC2 instance.
- AI dev prompts 路
Reference- A step-by-step Cursor workflow from idea to PRD to tasks, and the GPT-4.1 prompting guide.
Agents, memory, voice, and CI/CD pipelines.
- LangGraph 路
Tutorial- Stateful agents as graphs: chatbots, ReAct, RAG, memory, workflows, and subgraphs. - OpenAI Agents SDK 路
Tutorial- Guardrails, a manager agent, and router and triage patterns in Python. - MCP crash course 路
Course- Seven lessons on the Model Context Protocol for Python developers.
- Redis agent memory 路
Tutorial- Short-term and long-term memory for LangGraph agents on Redis. - Knowledge graph 路
Tutorial- Build a graph from text with an LLM, and a Neo4j quickstart.
- ElevenLabs voice agent 路
Project- A live voice agent that looks up patient records and books appointments.
- ML pipeline on GKE 路
Project- Train a model, serve it with Flask, and deploy to GKE with GitHub Actions.
- Context engineering 路
Reference- A context engineering template for AI coding assistants, with PRP commands.
Full services and production patterns.
- Agentic RAG with Redis 路
Project- A RAG graph on a Redis vector store, with query rewriting and relevance grading.
- GitHub sync 路
Project- A GitHub dashboard with a React client, a FastAPI server, and a Kafka pipeline.
- RAG on Kubernetes 路
Project- A RAG API on Kubernetes with Prometheus monitoring.
- AI code detector 路
Project- An Express and TypeScript service that asks Claude if code looks AI-generated, with GitHub webhooks.
- Hugging Face fine-tuning 路
Tutorial- Fine-tune Qwen3-0.6B for support ticket routing and compare metrics before and after.
Contributions are welcome. Read CONTRIBUTING.md first.
- Open a Module proposal issue for a new module.
- Fork the repository and create a branch.
- Improve a module, or add a new top-level folder for one.
- Copy the module README template. Add the module to the right tier above, with a type tag.
- Open a pull request. The template lists the checks.
Report a leaked secret through private reporting. Everyone must follow the Code of Conduct.
MIT. See LICENSE.
Created by Kushal Banda.