Open vs Trunchbull

Open-source RAG security toolkit with prompt injection detection, PII protection, secrets scanning, and retrieval integrity checks.

Provider-neutral AI model benchmarking. Detect regressions before they reach production.

About Open

Open-source RAG security toolkit with prompt injection detection, PII protection, secrets scanning, and retrieval integrity checks. AetherGuard AI is a unified zero-trust infrastructure for generative AI deployments, combining semantic security inspection, AI threat intelligence, cryptographic accountability, and hardware-rooted trusted execution into a single AI-native defense pipeline. Retrieval-Augmented Generation (RAG) has quickly become the standard architecture for enterprise AI applications. Much less attention is given to a fundamental question:. Traditional RAG pipelines assume that anything returned from a vector database is safe and trustworthy.

About Trunchbull

Provider-neutral AI model benchmarking. Detect regressions before they reach production. Deploy tools from GitHub, run them against managed AI models, and inspect every decision under controlled budgets. Trunchbull validates the contract, builds the repository, and deploys it into an isolated Cloudflare Worker, ready for any benchmark configuration. Give agents a real machine without giving them yours. Run terminal and code-execution evaluations inside controlled, image-backed environments. Define the maximum steps, token usage, and dollar spend before a run begins.