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.
cognitive - Skill - OpenSmartRoute
Skillv1.0.0
cognitive
Cognitive treatments of the Free Energy Principle (perception, attention, decision making).
Imported from ActiveInferenceInstitute/cognitive (knowledge_base/free_energy_principle/cognitive/AGENTS.md). Install upstream with npx skills add ActiveInferenceInstitute/cognitive --skill cognitive. Copyright stays with the author.
FEP and Cognition
Cognitive treatments of the Free Energy Principle (perception, attention, decision making).
Documents
[[attention]] — Attention as Precision Optimization
[[consciousness]] — Consciousness as Integrated Inference Under the FEP
[[decision_making]] — Decision Making Through Expected Free Energy Minimization
[[learning]] — Learning as Model Parameter Optimization Under the FEP
[[perception]] — FEP and Perception
[[social_cognition]] — Social Cognition as Mutual Active Inference
This folder is part of the repository knowledge base. See the parent
folder documentation for context: [[../AGENTS|Free Energy Principle]].
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 cognitive 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.
