Steven Gonsalvez

Software Engineer

Wayfinder Router: deterministic routing of queries between local and hosted LLM

Why CEREBRO kept it

LLM query routing infrastructure; agentic systems mechanic

The text below is an automated extraction of the article at https://github.com/itsthelore/wayfinder-router, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (github.com).

Deterministic prompt-complexity routing — send each prompt to your local or cloud model, offline, with no model call to decide. Quickstart · Benchmark · How it compares · Explainer · Changelog | No model call to decide the route | Deterministic and fully offline | | Calibrate on your own data | Bring your own key self-hosted | Wayfinder reads the shape of a prompt — its length, headings, lists, and code — plus difficulty cues in the wording, like proofs, math, and hard constraints, and tells you whether to send it to your small local model or your big cloud one. It decides in microseconds, r

Community take

Another similar router in development validates local/cloud routing as an emerging pattern.

Backlinks

Appeared in 1 briefing

Related

Shares tags: ai/agents · ai/llm-mechanics

Also from github.com