RUNTIME
DEFENSE FOR
AI AGENTS
The deterministic security architecture built for AI agents.
Lilith-zero SDK
Our first open source MCP middleware. Establish a deterministic security envelope for your agents in under 10 minutes.
Have feedback or found a vulnerability?
Lilith
Public Repository
gitcloneBadC-mpany/lilith-zeroPython SDK
uvaddlilith-zeropipinstalllilith-zeroENTERPRISE SOLUTIONS
Deterministic security for critical infrastructure
Security Audit
white-box assessment
- -attack surfaces
- -tool poisoning
- -MCP servers
- -Coding agents: (Claude Code, Codex, Copilots)
- -OpenClaw
- -discovery document + remediation plan
Securing MCP Agents
Deploying Lilith-zero to secure MCP servers and agents
- -Security middleware at the application layer
- -Agent scope definition
- -Policy set definition
- -Runtime observability
- -MCP native
- -Secure deployment of existing AI agents
Kernel-level Security
Lilith is an agent and os agnostic security layer
- -API access to NLP for precise and fine-grained policy definitions
- -Built on the kernel
- -Enterprise-grade security solution at the kernel-level
- -Full observability and logging
- -FIPS compliant
OPEN SOURCE RESEARCH
Publishing our findings to secure the future of AI
Red-Teaming Agent
A comprehensive framework for LLM safety through adversarial prompt generation and automated evaluation.
Hack the AI
Red-Teaming game where users hack realistic multimodal agent systems with RAG, memory, and tool usage.
CHIMERA
Cryptographic Honeypot & Intent-Mediated Enforcement Response Architecture
Agency Without Assurance
Investigating the security risks of autonomous agents with full computer access and OpenClaw configuration vulnerabilities.
STAY UPDATED
Get the latest research on agentic security and product updates directly to your inbox.
MEET THE TEAM
János Mozer
CEO
Physics background with experience in developing error-proof systems for distributed, resilient architectures, guaranteeing high availability through secure protocols.
Gregorio Jaca
RESEARCHER & ARCHITECT
Physics and Biology background. Worked on simulations from fluid dynamics and rockets to network systems. Currently researching LLM dynamics and interpretability through the lens of chaos theory.
Péter Tallósy
CTO
Physics-trained research engineer with deep expertise in ML/AI and full-stack software engineering capability. Experience in security and building directly on the hardware.