The AI-native collaboration layer for one-of-a-kind teammates and their agents: split a project into Artifacts with their own evals, and reuse every review…
Pure-Rust reader/writer for Python ML artefacts (npy, npz, pickle, pt, joblib, hdf5) with ndarray and polars interop, lazy streaming and user-controlled…
llama.cpp as a superfluid runtime: RuntimePrimitives over the libllama llama.cpp publishes, loaded at run time, for the generic executor; a vocab-only…