humanlayer/12-factor-agents

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

47
/ 100
Emerging

This project provides a set of guiding principles for software developers to build reliable and scalable AI-powered applications. It takes the complexities of integrating Large Language Models (LLMs) into software and outlines best practices. The output is more robust and maintainable LLM applications that can be confidently deployed to end-users.

18,686 stars. No commits in the last 6 months.

Use this if you are a software engineer or architect building production-grade applications that incorporate Large Language Models and want to ensure they are reliable, scalable, and maintainable.

Not ideal if you are looking for a pre-built agent framework or a plug-and-play solution, as this focuses on design principles rather than specific implementations.

AI application development LLM engineering software architecture production systems developer best practices
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

18,686

Forks

1,421

Language

TypeScript

License

Last pushed

Sep 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/humanlayer/12-factor-agents"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.