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.
scripts - Skill - OpenSmartRoute
Skillv1.0.0
scripts
This directory contains platform-specific wrappers around Docker Compose:
Imported from anirguha/The-Complete-Claude-Code-and-coding-agents (Projects/PM/scripts/AGENTS.md). Install upstream with npx skills add anirguha/The-Complete-Claude-Code-and-coding-agents --skill scripts. Copyright stays with the author.
Local container scripts
This directory contains platform-specific wrappers around Docker Compose:
start-mac.sh and start-linux.sh build and start the app in the background.
stop-mac.sh and stop-linux.sh stop/remove the app container while preserving the named pm-data volume.
start-windows.ps1 and stop-windows.ps1 provide the same operations in PowerShell.
The scripts resolve the project root relative to their own location. Keep them limited to Compose lifecycle commands; use docker compose down -v only when intentionally removing persistent database data.
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 - a plan picks it for its slotcurl-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}'
Installed into a catalogue, chosen by a router
Install scripts 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.
