OpenRouter's Ori agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → automates the configuration needed to connect an existing coding AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → to its model gateway. Its announcement uses Anthropic's Claude Code as an example: Ori launches the agent with connection settings and adjusts whether tool search is enabled according to the selected model. That capability is not supported uniformly across models, so a single fixed configuration can be a poor fit. Ori's role is to prepare the agent for the chosen backend while preserving its familiar commands and controls. The announcement describes additional model-specific tuning as future work.
Terms in this piece · Glossary
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
