@juspay/neurolink
Version:
The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002
17 lines (16 loc) • 749 B
JavaScript
/**
* Native skills support — versioned, discoverable instruction packs
* (SOPs, playbooks, workflows) exposed to the model via progressive
* disclosure: a cheap name+description index up front, full instructions
* loaded on demand through built-in skill tools.
*
* Architecture mirrors the Hippocampus memory subsystem: a `skills` config
* on the NeuroLink constructor lazily initializes a SkillsManager, which
* auto-registers built-in tools (list_skills, plus gated mutation tools)
* and augments each generate()/stream() call with the discovery listing
* plus per-call use_skill / read_skill_resource tools.
*
* Naming: every exported type carries a `Skill` prefix to satisfy the
* `unique-type-names` ESLint rule.
*/
export {};