AIAny
AI Agent2025
Icon for item

12-Factor Agents — Principles for building reliable LLM applications

Twelve engineering principles for building production-grade LLM agents, modeled on the 12-Factor App. Argues the best agents are mostly deterministic software with a few well-placed LLM calls, not a prompt-and-tools loop.

Introduction

Most agent frameworks get you to an 80% demo fast, then strand you — and the last 20% of reliability is exactly where production customers live. The bet here is counterintuitive: the agents that actually ship aren't autonomous loops at all, but mostly ordinary software with a handful of LLM calls placed precisely where judgment is genuinely needed.

Core Argument
  • Treat the twelve factors as a menu, not a religion. Each one — own your prompts, small focused agents, agent as a stateless reducer, trigger from anywhere — is a standalone pattern you graft onto existing code, so you gain control without rewriting your product around a framework.
  • Make the model's boundaries explicit. "Own your context window" means you decide exactly which tokens the LLM sees instead of trusting a framework's hidden serialization, and "tools are just structured outputs" reframes tool use as the model emitting JSON your deterministic code acts on — so every handoff between LLM and system stays inspectable, testable, and versioned.
  • Humans are a tool call, not an afterthought. "Contact humans with tool calls" plus launch/pause/resume APIs turn agents into durable, resumable workflows instead of fragile chat sessions that die on the first ambiguous step.
Who It's For + Tradeoffs

Great fit if you're a builder dragging an LLM feature from impressive demo to dependable production, and you want vendor-neutral patterns you can adopt piecemeal. Look elsewhere if you want a turnkey framework or an installable library — this is a set of principles, diagrams, and TypeScript examples, not a package, and it assumes you're comfortable owning your own control flow.

Information

  • Websitegithub.com
  • OrganizationsHumanLayer
  • AuthorsHumanLayer (Dex Horthy)
  • Published date2025/03/30

More Items

Turns fragile, implicit search progress into explicit, persistent, shared state for multi-agent information seeking — externalizes progress as Frontier Task, Evidence Graph, Coverage Map and Failure Memory, and uses pipeline-parallel scheduling plus a middleware harness to avoid repeated failed searches and improve utilization and throughput.

GitHub
AI Agent2026

Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.

GitHub
AI Client2025

Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).