kin-infer
kin-infer: how it fits into Kin.
This part runs the local calculations used for similarity search. It is a supporting component, not a general coding assistant.
How this works in Kin
Pure-Rust embeddings, computed locally.
Open source, Apache-2.0
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-benchPrivate supportPinned proof infrastructure. Public access is pending.
- kinlabHostedTeam collaboration built around open-source Kin.
- kinApache-2.0Kin is an open-source code repository for people and AI agents. It versions code and recorded relationships together. Give people a clearer basis for directing and reviewing AI-driven work.
- kin-dbApache-2.0An embedded graph engine, not a server you run.
Build, inspect or contribute.
Open source Kin gives you the local semantic system, and the install page has the commands for your platform. KinLab adds hosted collaboration for teams; you can request early access when a shared repository graph is what you need.