resk-logits
GPU-accelerated logits processor. Filters dangerous tokens during LLM generation using vectorized Aho-Corasick. Zero inference overhead.
pip install resklogits
██████╗ ███████╗███████╗██╗ ██╗
██╔══██╗██╔════╝██╔════╝██║ ██╔╝
██████╔╝█████╗ ███████╗█████╔╝
██╔══██╗██╔══╝ ╚════██║██╔═██╗
██║ ██║███████╗███████║██║ ██╗
╚═╝ ╚═╝╚══════╝╚══════╝╚═╝ ╚═╝
AI systems have access to your most sensitive data. They remain critically vulnerable.
Enterprise Code Security Crisis
AI systems today have access to source code, customer records, financial data, and internal communications -- yet every unsecured integration is a potential breach. Prompt injections, data leakage, and unauthorized tool calls are not theoretical risks. They are happening now.
50,000+
Enterprises using AI coding tools
100M+
Lines of code generated daily
70%
Organizations lacking AI governance
(Sources: Cursor, PwC)
Open Source Tools
reskSecure
Bitmask-based LLM security firewall. Restricts model output based on user permission bitmasks with YAML policy and tool call prevention.
pip install resksecure
ReskPoints
The AI Agent Logger. Track every action your agents take. Ship to Datadog, Prometheus, OpenTelemetry, webhooks, or file.
pip install reskpoints
resk-llm
Python library for securing LLM API interactions. Protects against prompt injections, PII leaks, and malicious URLs.
pip install resk-llm
resk-llm-ts
TypeScript security toolkit for LLM integrations. OpenAI-compatible wrapper with built-in defenses.
npm install resk-llm-ts
mcp-resk
Security layer for the Model Context Protocol (MCP) Python SDK. Monitoring, validation, and protection for MCP workflows.
pip install mcp-resk
Upcoming Projects
RESK Monitor
LLM deployment monitoring with real-time error rate calculation and behavioral deviation detection.
In Development
ReskCrypt
End-to-end encryption for AI conversations with AES-256-GCM and ECDSA digital signatures.
Learn moreGnom
Graph Neural Network monitoring for real-time threat detection and network topology analysis.
Learn moreReskLayer
Advanced prompt injection detection using ModernBERT with DiffTransformer attention.
Learn moreExplore Our Security Resources
Research papers, implementation guides, and security insights for AI deployments.