kin-infer
kin-infer: local inference
Pure-Rust embeddings, computed locally.
A pure-Rust, GPU-accelerated inference and embedding engine that computes embeddings locally, with no external inference service required.
How it relates to Kin
Produces the embeddings that power Kin semantic retrieval.
Related surfaces
Kin is one system with a few clear surfaces. Explore how the rest of the ecosystem fits together.
Kin is the system of record for AI-written software. Kin keeps a persistent graph of entities, relationships, changes, and history.
An embedded graph engine, not a server you run.
Serve graph-backed files to ordinary filesystem tools.
Kin in your editor, not a fork.
One system. A few clear surfaces.
Open source Kin gives you the local semantic system. KinLab adds hosted collaboration for teams. Install Kin, or request early access to KinLab.