Verified project record

humanlayer/12-factor-agents

A principles-based guide for engineers who need to make LLM-powered software production-ready. It documents modular agent concepts, context-window management, and tool-call design for integration into existing products.

Project overview

Project type: AI Agent
Use cases: Learning & Education
Deployment: Refer to project documentation
License: License pending

Best for

Developers and AI engineers looking for structured principles to improve the reliability and maintainability of LLM applications.

Key capabilities

Documents modular agent-building concepts that builders can incorporate into existing products.
Includes a factor covering ownership of an LLM application's context window.
Includes a factor covering natural-language-to-tool-call design.

Limitations and risks

Requirements for GPU usage, operating system, database dependencies, minimum hardware, and external services are not documented.
The guide focuses on applying small, modular concepts rather than providing a comprehensive framework rewrite.

Getting started

Setup difficulty, prerequisites, and initial steps are not documented.

Evidence and sources

GitHub project description: 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?
README: Even if LLMs [continue to get exponentially more powerful](https://github.com/humanlayer/12-factor-agents/blob/main/content/factor-10-small-focused-agents.md#what-if-llms-get-smar…
README: The fastest way I've seen for builders to get good AI software in the hands of customers is to take small, modular concepts from agent building, and incorporate them into their ex…
README: - [Factor 3: Own your context window](https://github.com/humanlayer/12-factor-agents/blob/main/content/factor-03-own-your-context-window.md)
README: - [Factor 1: Natural Language to Tool Calls](https://github.com/humanlayer/12-factor-agents/blob/main/content/factor-01-natural-language-to-tool-calls.md)

Reviewed at: 2026-07-17T10:48:48Z