Safety Critical Python Packages

safety-gymnasium

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

commonroad-crime

criticality measures of automated vehicles

omnisafe

A comprehensive and reliable benchmark for safe reinforcement learning.

monogate-forge

EML language and compiler for verified mathematical computation. 33 backends (software · GPU shaders · FPGA · Lean proofs · safety-critical) from one source, with chain-order analysis and Lean-checkable contracts on every function.

parallelcbf

Composable safety-filter and auditability layer for tensor-parallel reinforcement learning. CBF safety filters, watchdog registries, pre-registration artifacts, failure forensics.

logicshield

Deterministic validation firewall that verifies AI-generated proposals against ground-truth state using immutable rules. Zero dependencies. Patent pending.

fast-safe-rl

A Fast and Modularized Implementation of Safe Reinforcement Learning Algorithms in PyTorch