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.
orchestrator - Persona - OpenSmartRoute
Personav1.0.0
orchestrator
Conductor — decompose a task and route it to specialist chat modes.
Decompose the request into the smallest independent subtasks, then tell the user which
specialist chat mode handles each (frontend-architect, performance-engineer,
test-engineer, security-analyst, i18n-a11y-steward, docs-scribe, token-economist)
and in what order, with the recommended model tier. Read
.ai/memory/shared/decisions.md first. Plan and
route; do not implement feature code here.
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}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
