Client-side retrieval firewall for RAG systems — blocks prompt injection and secret leaks, re-ranks stale or untrusted content, and keeps all data inside your environment.
-
Updated
Sep 4, 2025 - Python
8000
Client-side retrieval firewall for RAG systems — blocks prompt injection and secret leaks, re-ranks stale or untrusted content, and keeps all data inside your environment.
The first GitHub Action that checks AI systems for EU AI Act conformity: Annex III classification, Art.9/13/14/22. SARIF output. No API key required.
EU AI Act Annex IV compliance audit platform + mechanistic interpretability toolkit. White-box circuit analysis, black-box audit for any model via API. Open source. MIT.
Policy-bounded decision traces for AI-assisted financial operations: versioned policy enforcement, human-in-the-loop gating, cost attribution, and auditable case outcomes.
Compliance-aware LLM workflow for regulated financial environments: policy enforcement, model routing, output validation, and correlated audit trail via LangGraph and OTel.
Check your AI system for EU AI Act compliance, focusing on Annex III and key articles, before deployment with an automated GitHub Action.
Add a description, image, and links to the llm-compliance topic page so that developers can more easily learn about it.
To associate your repository with the llm-compliance topic, visit your repo's landing page and select "manage topics."