LuaN1aoAgent is a cognitive-driven AI hacker. It is a fully autonomous AI penetration testing agent. Using dual-graph reasoning, LuaN1ao achieves a success rate of over 90% on the XBOW Benchmark.

Tutorials on Causal Inference and pgmpy

Algorithms for quantifying associations, independence testing and causal inference from data.

Open-source causal graph memory for AI agents. 89.9% on LoCoMo. MCP server with ACT-R scoring, spreading activation, and active forgetting.

CausIL is an approach to estimate the causal graph for a cloud microservice system, where the nodes are the service-specific metrics while edges indicate causal dependency among the metrics. The approach considers metric variations for all the instances deployed in the system to build the causal graph and can account for auto-scaling decisions.

A curated list of amazingly awesome things regarding Graph Structure Learning.

🔎 Benchmarking Framework for Extendability of Causal Graphs 🔍

🧠 R2T Prototype: An LLM pre-trained on causal graphs (not just text) to build provably faithful step-by-step reasoning.

🧠 Implement a bi-factual contrastive explanation system for AI decisions, enhancing understanding through formal definitions and optimized algorithms.

Logistic optimization: Delivery drivers location optimization with Causal Inference

A Minimal model for causal invariance: path merging via DP-like optimization

🔍 Enhance reasoning accuracy with the Reflective Reasoning Transformer, leveraging causal reasoning graphs for better dynamic reasoning performance.

Implémentation d’un système d’IA Explicable (XAI) basé sur les explications contrastives bi-factuelles, avec optimisations algorithmiques et interface graphique CausaLytics.

Code for the python model `actualcauses` that implements algorithms for HP-causes identification.

R code for causal graph animations

Investigating how formal constraints reorganize the internal routing geometry of Transformer attention graphs across model families.

Persistent causal memory for AI coding assistants.

Federated anomaly detection and automated root cause analysis for massive microservice architectures.

QIC-S Theory Ver 1.6: Numerical codebase (partially retracted, see ERRATUM). DOI: 10.17605/OSF.IO/KB75P