Tiny byte-level AI on CPU: zero-dependency C++20 inference engine and neural decision models (2.8ms latency, 9.4MB RAM). Replaces tokenizers with a 256-byte vocabulary. Flagship specialists for pre-commit secret scanning (0.797 F1 vs 0.337 GitLeaks) and PII redaction. Apache 2.0.
python machine-learning pre-commit simd cybersecurity byte-level inference-engine cpp20 zero-dependencies pii-redaction cpu-inference secrets-scanner gguf dev-secops
-
Updated
Sep 28, 2026 - C++