Ori puts the whole OpenRouter catalog behind DeepSeek's harness
- Source
- x.com
- Date
Today, we are launching Ori DeepSeek Harness Run @deepseek_ai Harness on your whole OpenRouter catalog. One setup command wires your credentials, 500+ models, and routing into your own harness home $ curl -fsSL https://t.co/vROsUW01Hr | bash $ ori deepseek
Ori DeepSeek puts your entire OpenRouter catalog in the harness. Claude, GLM, Kimi, and the rest, in the interface you already use. DeepSeek Harness, but with the 500+ models on OpenRouter you have access to.
Don't have DeepSeek Harness already? We will install it for you. No YAML to hand-edit and no existing dsh configs to lose. Your key goes to the harness's credential store, not into your settings file or your shell history.
Ori DeepSeek refreshes your OpenRouter catalog on every boot, so new models show up without you touching config again. Add /fast on for speed routing or /zdr on to restrict the session to zero-retention providers.
Context
Ori connects DeepSeek , the software surrounding a coding model, to the model catalog available through OpenRouter. The launch thread describes setup that supplies credentials, model choices and routing while refreshing the catalog at startup. The useful separation is between the interface a developer works in and the model doing the work: changing models need not mean changing the surrounding application. OpenRouter's current Ori Harness page also documents DeepSeek Harness support and model selection.
- 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.
Checking sign-in…
Loading comments…