workflowstacks
mcp-server

Agents Towards Production

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.
21,323 stars2,832 forksJupyter NotebookUpdated 8/15/2026100% free · open source
What it does

Provides step‑by‑step Jupyter notebooks and scripts to turn a prototype LLM agent into a production‑ready, containerized service.

Install / run
git clone https://github.com/NirDiamant/agents-towards-production.git && cd agents-towards-production && pip install -r requirements.txt
When to use it
  • •You have a working LangChain/LlamaIndex agent prototype and need a reproducible deployment pipeline.
  • •Your startup wants to expose an LLM‑driven assistant as an API behind authentication and scaling controls.
  • •You need a reference implementation that shows how to add logging, monitoring, and CI/CD for GenAI agents.
Quick start
  1. 11️⃣ Export your OpenAI key: `export OPENAI_API_KEY=sk-...` (required for all notebooks).
  2. 22️⃣ Launch the tutorial notebook: `jupyter lab notebooks/01_build_agent.ipynb` and run the cells to create a basic LangChain agent.
  3. 33️⃣ Test the agent locally with the CLI helper: `python scripts/run_agent.py "What is the net revenue growth Q1 2024?"`.
  4. 44️⃣ Build the Docker image for production: `docker build -t genai-agent .`.
  5. 55️⃣ Deploy with Docker Compose (includes FastAPI wrapper, Prometheus, and Grafana): `docker compose up -d`.
Ready-to-paste prompt
python scripts/run_agent.py "Extract all action items from the attached PDF of our last board meeting and email them to the CFO."
Heads up: The first run fails if `OPENAI_API_KEY` is not set in the environment; the notebooks and scripts exit with a clear “API key missing” error.
Saves to your device

Topics

agent
agent-framework
agentic-ai
agents
ai-agents
deployment
genai
generative-ai
langgraph
llm
llms
mcp
mlops
multi-agent-systems
observability
production
python
rag
tutorials
What's inside — free to inspect
No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

4
top-level files
4
folders
153.8M
source size
Other
license
Key files
README.md
File tree
.github/
assets/
images/
tutorials/
.gitignore
CONTRIBUTING.md
LICENSE
README.md
Quick Actions
Details
Creator
NirDiamant
Language
Jupyter Notebook
Category
mcp-server
Published
6/16/2025

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 242,984
ECC: Optimize Performance
Get optimized performance with ECC, a research-first agent harness system for founders working with AI agents and developer tools like Claude Code and Codex
mcp-server★ 153,719
Dify: Streamline Workflow
Get a production-ready platform with Dify. For founders needing agentic workflow development.
mcp-server★ 150,115
open-webui: Easy AI Interface
Get a user-friendly AI interface with open-webui, supporting Ollama and OpenAI API, for founders, with 145k+ GitHub stars
mcp-server★ 106,674
gemini-cli: AI in your terminal
Get AI power with gemini-cli, for founders, 105k+ GitHub stars
mcp-server★ 82,036
LobeHub: 24/7 AI Team Management
Founders get organized AI operations with LobeHub. For startup founders managing AI teams.
mcp-server★ 76,702
Worldmonitor: Global Awareness
Get real-time global intelligence with worldmonitor, a unified dashboard for startup founders and teams, with 61k+ GitHub stars