jailguard 0.1.0

Pure-Rust prompt-injection detector with 1.5MB embedded MLP classifier. 98.40% accuracy, p50 14ms CPU inference, 8-class attack taxonomy. Apache-2.0/MIT alternative to Rebuff and Lakera Guard.
Documentation

jailguard

There is very little structured metadata to build this page from currently. You should check the main library docs, readme, or Cargo.toml in case the author documented the features in them.

This version has 10 feature flags, 0 of them enabled by default.

default

This feature flag does not enable additional features.

c-api

This feature flag does not enable additional features.

cpu

This feature flag does not enable additional features.

download

full

napi

pretrained

pyo3

python

semantic-embeddings

This feature flag does not enable additional features.

training