4 projects
benchcraft-clean
Benchcraft Data-Quality: ONNX Runtime (PyTorch-free) text embeddings feeding naive cosine-similarity near-duplicate detection (D4 scaffold).
benchcraft-automl
Benchcraft AutoML: clean-room tabular AutoML. This scaffold-depth pass implements .compile() -- fusing a fitted sklearn.pipeline.Pipeline into a single ONNX graph via skl2onnx.
benchcraft-agent
Benchcraft Agent: a bring-your-own-agent AgentAdapter pattern -- a rule-based reference agent executes file-manipulation tool-use tasks through the shared lazycore sandbox executor, scored for success/latency and reported via OTel GenAI telemetry.
benchcraft-core
Benchcraft Core: the thin, shared substrate used by all Benchcraft modules (data-tier conventions, OTel GenAI telemetry helpers, license-isolation policy).
