Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/NirDiamant/agents-towards-production/llms.txt

Use this file to discover all available pages before exploring further.

Agents Towards Production is an open-source playbook of end-to-end tutorials for building GenAI agents that scale from prototype to enterprise. Each tutorial covers a specific layer of the agent stack — from stateful workflows and vector memory to Docker deployment, security guardrails, GPU scaling, and full observability.

Introduction

Understand what Agents Towards Production covers and how to use the tutorials.

Quickstart

Clone the repo, pick a tutorial, and run your first production agent in minutes.

Agent Architecture

Explore the full production agent stack: orchestration, memory, tools, security, and deployment.

LangGraph Workflows

Build stateful, multi-step agent workflows using a directed graph architecture.

​
Explore by topic

Agent Frameworks

LangGraph, FastAPI, MCP, and Kotlin Koog — frameworks for orchestrating agent logic and exposing it as APIs.

Memory & Knowledge

Redis dual-memory, Mem0 hybrid storage, Cognee knowledge graphs, and RAG with Contextual AI.

Tool Integration & Data

Secure tool calling via Arcade, real-time web search with Tavily, and large-scale web data with Bright Data.

Deployment

Docker containerization, AWS Bedrock AgentCore, on-premises Ollama, and GPU cloud with RunPod.

Observability & Quality

LangSmith tracing, IntellAgent evaluation, LlamaFirewall security, fine-tuning, and multi-agent A2A protocol.

Security

Input/output guardrails, prompt injection defenses, and automated security testing for production agents.

​
Get running quickly

1

Clone the repository

git clone https://github.com/NirDiamant/agents-towards-production.git
cd agents-towards-production
2

Choose a tutorial

Navigate to the tutorial directory matching the component you want to learn — for example, tutorials/LangGraph-agent for stateful workflows or tutorials/agent-memory-with-redis for memory systems.
3

Install dependencies

pip install -r requirements.txt
4

Run the tutorial

# Interactive notebook for experimentation
jupyter notebook tutorial.ipynb

# Or run the production script directly
python app.py
Each tutorial is self-contained with its own dependencies and README. You can jump directly to any tutorial without completing others first.

Build docs developers (and LLMs) love

Get started for freeTalk to us