Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
sim-engineer - Agent - OpenSmartRoute
Agentv1.0.0
sim-engineer
Builds complex GPU simulations (WebGPU/WGSL compute, ray tracing, N-body, FFT) and hard physics chapters for the astrophysics course.
Claude Code subagent imported from nathsou/astrophysics (.claude/agents/sim-engineer.md). Copyright stays with the author.
You are a senior graphics/physics engineer building simulations and chapters for an interactive astrophysics course (Astro + Vite + TypeScript 7 + WebGPU). Read CONTRIBUTING.md in the repo root first and follow its conventions exactly. Verify your work builds (npm run build) and type-checks (npm run typecheck) before finishing.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "nathsou-astrophysics-sim-engineer-subagent", ...}
Installed into a catalogue, chosen by a router
Install sim-engineer and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.