The Harness Playbook — Stencil
Model the agentic harness like a game engine and most of its hard problems — durable state, tools, configuration, the TUI, inference — collapse into ones other people already solved.
Before anything else: a thank you. Hundreds of thousands of you have used omp, reported what broke, suggested what was missing, and shaped what it became. This post and omp² itself exist because of you. Upon hearing about omp², many of you jumped to ask, "but why?" A while loop around a fetch sounds simple, but there's a reason OpenCode, Pi, OpenClaw and omp are all concurrently working on a complete refactor: this class of software did not exist before, and only by starting with the simple version, we could see the cracks to work towards a better one. Unavoidable complexity needs an…
saved by
related reading
- Building a harness for open modelsparthsareen.com
- What is an Agent Harness?rubriclabs.com
- Lecture 01. Strong Models Don't Mean Reliable Execution | Learn Harness Engineeringwalkinglabs.github.io
- Harness Engineering for Self-Improvement | Lil'Loglilianweng.github.io
- How to Harness Coding Agents with the Right Infrastructure | Blogalexlavaee.me
- Arjun Virkarjunvirk.com
- exoharnessexoharness.ai
- Welcome to Learn Harness Engineeringwalkinglabs.github.io
- Continually improving our agent harness · Cursorcursor.com
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- Scaling Managed Agents: Decoupling the brain from the hands \ Anthropicanthropic.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com