Work smarter with AI — not harder with hype.

open-agency is a free, open-source site for people building with AI. Read practical guides and use the local model calculator to choose a model for your device.

Browse the guides See the tools

Free, open-source, and practical — no account required to get started.

Open source systems

Practical guides and a local model calculator for building with AI without hiding the human review loop.

Open source — practical guides and tools are built in public
No fluff — guides ship with working code, not slides
Built by practitioners — platform engineers and creators, not influencers

Latest guides

Fresh operating notes from the Open Agency guides library.

See all guides

Multi-Model Routing: The Highest-ROI Pattern in Your Agentic Stack

AI Infrastructure

Sep 6, 2026

Multi-Model Routing: The Highest-ROI Pattern in Your Agentic Stack

Learn how routing across multiple LLM providers cuts costs 40-85% while maintaining quality, with concrete patterns for static rules, classifiers, embeddings, and hybrid approaches.

Read article

Agent Guardrails Architecture: Building Safety Into Multi-Step Workflows

AI Infrastructure

Sep 5, 2026

Agent Guardrails Architecture: Building Safety Into Multi-Step Workflows

A practical guide to designing three-layer guardrails, confidence-based escalation, and human-in-the-loop checkpoints for AI agents that actually work in production.

Read article

Context Rot: The Silent Killer of Long-Running AI Agents

LLM Engineering

Sep 3, 2026

Context Rot: The Silent Killer of Long-Running AI Agents

Context rot degrades your agent's output long before the context window fills. Here's why it happens, how to measure it, and what actually works to stop it.

Read article

Production Agentic AI: Lessons from 83% Cycle-Time Reductions in Claims Processing

AI Strategy

Sep 2, 2026

Production Agentic AI: Lessons from 83% Cycle-Time Reductions in Claims Processing

The architecture pattern behind production agentic AI isn't about the model. It's about routing cheap models for retrieval and triage, reserving frontier models only for reasoning-critical paths.

Read article

Free tools. No account needed.

Choose a local AI model for your device and workflow goals.

Local model calculator
Find the best local AI model for your device specs and workflow goals.
Explore

Work smarter with AI — not harder with hype.

Multi-Model Routing: The Highest-ROI Pattern in Your Agentic Stack

Agent Guardrails Architecture: Building Safety Into Multi-Step Workflows

Context Rot: The Silent Killer of Long-Running AI Agents

Production Agentic AI: Lessons from 83% Cycle-Time Reductions in Claims Processing

Local model calculator

Weekly notes for teams designing with AI instead of around it.