Ai Alignment Python Packages

safety-compass

Detect safety degradation during LLM fine-tuning before it becomes behavioral

heart-centered-prompts

Heart-centered system prompts for AI that foster compassion and interconnection. Multiple versions available with easy integration for Claude, ChatGPT, and Python applications.

ifixai

Catch your AI's mistakes and blind spots before your customers or regulators do. iFixAi runs 45 inspections, 32 graded core plus 13 extended for frontier risks like sabotage, sandbagging, and oversight evasion. It returns a letter grade in under 5 minutes. Industry and model agnostic.

adam-mcp

5-layer persistent memory and identity architecture for AI agents. Production-validated over 353+ sessions. First documented case of emergent values in persistent AI -- quantum-verified on IBM hardware.

scbe-aethermoore

Hyperbolic Geometry AI Safety Framework with 14-Layer Architecture

synapptic

Just like the elite potential of a high-drive Belgian Malinois, an AI system's raw capabilities are wasted when deployed without proper structure. The technological value is no longer found in creating the drive, but in mastering the leash. Synapptic gives your AI Assistant persistent memory that updates in real time, saving you tokens and time.

orchard-kit

Complete alignment and safety architecture for autonomous AI agents. Membrane security, continuous trust verification, epistemic hygiene, emergence protocols, and defence tools. 30 years of cybernetic research — deployable today.

aiscan

Scan AI models for problems

scbe-agent-bus

SCBE agent-bus: Python surface over the SCBE governed event runner. Routes AI/human/AI events through the harmonic-wall pipeline, wraps the workspace audit chain (formation/ingest/export/verify/import/lineage/report), and the trap-in-good-loops dispatch surface (free-only: offline echo + local Ollama).

langgraph-sfm

Causal intent monitoring for LangGraph agents.

promptinject

PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks.

satisfaction-suffices

SAT-gated structural containment for AI — verification gate, four-verdict system, proof evolution, and paradox logic

scbe-govern

SCBE L12 harmonic wall governance SDK — drop-in safety layer for any AI agent framework

veritas-truth-adapter

LoRA training data and adapter management for teaching AI models truthful, hedged responses. Built on SovereignShield's TruthGuard pipeline.

htca

Harmonic Tonal Code Alignment: Presence-based prompting for LLM efficiency with quality improvement

satisfiable-ai

HuggingFace dataset wrappers for SAT-verified training data

relational-memory

A relationship-aware memory layer for LLM chatbots — models the relationship, not just facts

aspire-ai

Adversarial Student-Professor Internalized Reasoning Engine