Model Agnostic Python Packages

clsplusplus

Brain-inspired, model-agnostic persistent memory for LLMs. Learn, recall, forget — like a brain. Works with OpenAI, Claude, Gemini, Llama.

helix-adapter

Portable constitutional adapter for any LLM. Forces epistemic markers ([FACT], [REASONED], etc.), real-time drift detection, and tamper-evident receipts. Model-agnostic wrapper.

cybnodes

Entoure ton LLM de reseaux de capacites verifiables (calcul, savoir, web), et redit chaque resultat dans sa voix. Model-agnostic, sans dependances.

aime-xai

AIME (Approximate Inverse Model Explanations) — inverse-operator XAI with publication-grade visualisations and an inverse-explanation evaluation suite.

hcc-field

**HCC can accompany you for a lifetime**

sinq

Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy [ICML 2026]

simplemaml

A generic Python and TensorFlow function that implements a simple version of the "Model-Agnostic Meta-Learning (MAML) Algorithm for Fast Adaptation of Deep Networks" as designed by Chelsea Finn et al. 2017

slise

The SLISE algorithm for robust regression and explanations of black box models

gemex

GEMEX: Geodesic Entropic Manifold Explainability — novel model-agnostic XAI grounded in Riemannian information geometry

hummcode

The Hummingbird Coding Agent — minimalist, powerful, model-agnostic, and composable.

tsproto

Post-hoc prototype-based explanations with rules for time-series classifiers