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.
hive-storage - Skill - OpenSmartRoute
Skillv1.0.0
hive-storage
Hand-written Hive models and TypeAdapters — stable typeIds, backward-compatible reads
Instruction file imported from ZanderCowboy/sprout (.cursor/rules/hive-storage.mdc). Copyright stays with the author.
Hive storage
Adapters are checked in at sprout_app/lib/core/storage/hive_adapters.dart. Do not generate them.
Never reuse or reshuffle typeIds (0 account … 4 budget group). New models get the next unused id and a HiveBoxes name.
read order must match write order. New fields are appended; old rows must still deserialize (see TransactionHiveAdapter).
Map Hive DTOs in data/mappers/**, not in presentation.
More: .cursor/references/offline-sync.md.
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 slot
curl -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 hive-storage 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.