Search

Google T5, or Text-to-Text Transfer Transformer, is a powerful model that revolutionizes the way natural language processing tasks are handled. By converting various language processing problems into a text-to-text format, T5 allows for a unified approach that simplifies and enhances the user's experience. This innovative framework is designed to handle a wide range of tasks such as translation, summarization, and question answering, making it incredibly versatile for developers and businesses a

LlamaIndex.TS connector for BonkLM - RAG query and retrieval validation

> A proof of concept to allow users with Overall/Read permission and Job/Configure (and optional Job/Build) to bypass the sandbox protection and execute arbitrary code on the Jenkins master or node.

Leaderboard management and result comparison for prompt-injection-bench

Claude Code 技能：客户端软件全维度防破解安全审计（7大通用维度 × 9个平台专项）

Mistral SDK v2 wrapper for BonkLM — chat/agents/fim/embeddings/classifiers guardrails with default-on multilingual + reformulation detection

Encrypt/Decrypt the values of a given object

Save a secret: a small window opens that Claude cannot see, you paste there, it lands in 1Password. Read it back: any item in your vault loads into Claude with one fingerprint check, names only, never the values. Keys you paste in the chat are deleted before Claude reads them. Mac, Windows, Linux. MIT.

Audit any Strapi CMS for public-role data exposure, CORS reflection, user enumeration and GraphQL introspection — and PROVE each leak live with an anonymous probe. No admin token needed for the keyless scan.

ESLint rules that AI assistants can actually fix - error messages optimized for both human developers and Large Language Models

JavaScript API library for the ADAMANT Blockchain

Sanitizes external content to prevent Indirect Prompt Injection in RAG systems.

Async LLM jailbreak / prompt-injection fuzzer for OpenAI-compatible chat completion endpoints.

Znyx guardrails runtime: a lightweight FastAPI service that evaluates LLM traffic against policies. Rules-only out of the box; gains ML when pointed at a Znyx inference sidecar.

A solid TypeScript-based ESLint plugin infrastructure inspired by typescript-eslint

Static due-diligence scanner for local AI model artefacts and repositories.

AI Governance-as-Code CLI — discover, classify, and govern AI systems

Check what an LLM is given for prompt injection: material at ingest, and the turn it answers

AI LLM Firewall -- Runtime defense for LLM applications against prompt injection, jailbreak, and adversarial attacks

Themis React Native is a convenient cryptographic library for data protection