les dejo uno de los mejores papers que leí sobre Harness Engineering.
explica muy bien:
1) qué es un harness
2) cómo están construidos los coding agents actuales
3) qué patrones se repiten entre Claude Code, Codex, Gemini CLI, etc.
4) hacia dónde está evolucionando la categoría
5) qué recomiendan si querés construir uno
todo parte de una definición simple:
Agent = Model + Harness
como complemento, también pueden leer el artículo que escribí sobre el tema.
paper:
https://t.co/xTvb7MvzQG
Andrej Karpathy spent 8 years at OpenAI and Tesla
last week, he packed everything he knows into one free 2-hour lecture
Agents → Loops → Harness → Self-Improving Systems
people spend $25K on bootcamps that teach less than this
this lecture is worth more than most paid AI engineering courses
you probably don't have two hours for it right now
don't let it get buried in your feed
bookmark it and watch later
then read the full article below
Finally, an OpenRouter for agent harnesses!
(including System One by Jev)
Devs just open-sourced a plug-and-play infrastructure layer that lets you run any harness under a single interface, like:
- Codex
- Hermes
- Claude code
- DeepSeek Harness
- System One, powered by Jev
- And 9 more agent harnesses
This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling.
Here's the repo: https://t.co/scJwb2xUyM
(don't forget to star it ⭐ )
The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API.
If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses.
It also covers UHP, the full local setup, a working API call, and how sessions and files work.
Read it below.