RUNTIME
DEFENSE FOR
AI AGENTS

The deterministic security architecture built for autonomous AI systems.

>curl -sSfL badcompany.xyz/lilith-zero/install.sh | sh

Open Source

Lilith SDK

Our first open source MCP middleware. Establish a deterministic security envelope for your agents in under 10 minutes.

EXPLORE DOCS STAR ON GITHUB

Have feedback or found a vulnerability?

Lilith

Public Repository

gitcloneBadC-mpany/lilith-zero

Python SDK

uvaddlilith-zero

pipinstalllilith-zero

ENTERPRISE SOLUTIONS

Deterministic security for critical infrastructure

WORKSTATION SIDE

SECURE ENVIRONMENT

Verified gateway for high-assurance use of agents.

/Verified agentic browsing
/Verified agentic coding
/Observable activity
/No API leak
/No bloatware install
/No network exploit

SELF-DEPLOYED AGENTS

SECURE DEPLOYMENT

Verified execution container for autonomous AI agents.

/Agent swarms verified
/No leftover zombie processes
/No data exfiltration
/No bloatware install
/No sensitive data leak
/No unauthorized database access

COMBINED PROTECTION

COMPLETE SOLUTION

End-to-end protection for critical IP and regulated data, on both agent and user side.

/Confidential information obfuscation
/Full audit trail for FDA
/Encrypted inference
/Model weight protection
/Zero-trust data ingress

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.

Python→

Hack the AI

Red-Teaming game where users hack realistic multimodal agent systems with RAG, memory, and tool usage.

TypeScript, Python, LangChain→

CHIMERA

Cryptographic Honeypot & Intent-Mediated Enforcement Response Architecture

Python→

Agency Without Assurance

Investigating the security risks of autonomous agents with full computer access and OpenClaw configuration vulnerabilities.

Security Audit→

MEET THE TROUBLEMAKERS

The rebels behind the code

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.

RUNTIMEDEFENSE FORAI AGENTS