Agentic Ai Security Python Packages

rlm-toolkit

AI Security Platform: Defense (61 Rust engines + Micro-Model Swarm) + Offense (39K+ payloads)

sentinel-llm-security

AI Security Platform: Defense (61 Rust engines + Micro-Model Swarm) + Offense (39K+ payloads)

ectoledger-sdk

The dashcam and emergency brake for AI agents. A security proxy that physically blocks rogue LLM commands and generates cryptographically proven audit trails for enterprise compliance.

constrai

Formal safety framework for AI agents. Pluggable LLM reasoning constrained by mathematically proven budget, invariant, and termination guarantee. 7 theorems enforced by construction, not by prompting. Includes Bayesian belief tracking, causal dependency graphs, sandboxed attestors, environment reconciliation, and a 155-test adversarial suite.

clampai

Safety guardrails for LLM agents — budget enforcement, invariants, and provable guarantees. Zero dependencies.