All activity
reskleft a comment
🛡️ 800 downloads in just 3 days: The LLM security market has spoken. Meet ReskLogits, the library redefining content moderation for Generative AI! Say goodbye to abrupt Hard Blocks. Hello to the invisible Shadow Ban. ReskLogits is an innovative logits processor that doesn't outright ban, but subtly penalizes dangerous tokens. How it Works? We use a vectorized Aho-Corasick algorithm (GPU/CPU...
GitHubResklogits is a tokens processor that implement a shadow ban
reskleft a comment
Resk-Caching is a Bun-based backend library/server designed to cache Large Language Model (LLM) responses using vector databases, significantly reducing API costs while maintaining response quality and relevance. 🎯 Primary Purpose: Cost Optimization for LLM APIs This library addresses the high costs associated with LLM API calls by implementing intelligent caching strategies. Instead of making...
ReskCaching Resk-caching is library for secure caching, LLM's response.
Resk-Caching is a Bun-based backend library and server designed for secure caching, embeddings orchestration, and vector database access. It prioritizes security, high performance, and deep observability. - Resk-Security/resk-caching
ReskCaching Resk-caching is library for secure caching, LLM's response.
reskleft a comment
Why Resk-LLM-TS? As LLMs become integral to modern applications, securing them against vulnerabilities like prompt injections and data leaks is critical. Resk-LLM-TS offers a comprehensive, open-source solution that integrates seamlessly with JavaScript/TypeScript environments, making it accessible for developers of all skill levels. Its customizable security modules and support for Node.js and...
Resk LLM TSSecure your LLM integrations with ease
Resk-LLM-TS is a powerful security toolkit for JavaScript and TypeScript applications leveraging Large Language Models (LLMs). It wraps OpenAI-compatible APIs (like OpenAI and OpenRouter) to protect against prompt injections, data leaks, and other threats.
Resk LLM TSSecure your LLM integrations with ease
reskleft a comment
RESK-LLM is a comprehensive security toolkit for Large Language Models (LLMs), designed to protect against prompt injections, data leakage, and malicious use. It provides robust security features for multiple LLM providers including OpenAI, Anthropic, Cohere, DeepSeek, and OpenRouter.
Resk-LLMGitHub repository for building secure GenAI applications.
Resk is a robust Python library designed to enhance security and manage context when interacting with OpenAI's language models. It provides a protective layer for API calls, safeguarding against common vulnerabilities and ensuring optimal performance.
Resk-LLMGitHub repository for building secure GenAI applications.