Map / Runtime & Guardrails / Lakera
Lakera
lakera.ai ↗ · LinkedIn ↗ · Open on the map
Runtime & GuardrailsAI Red TeamingMCP & LLM GatewaysModel Security
Capabilities
AI-native security platform for agentic AI applications; flagship products Lakera Red (continuous AI red teaming) and Lakera Guard (real-time runtime enforcement); detection rates above 98% with sub-50ms latency and false positives below 0.5%; protection across prompts, RAG pipelines, MCP, and multi-agent workflows; powered by Gandalf adversarial red-teaming community with 80M+ adversarial patterns; supports 100+ languages.
Sensors / integration
API-based and cloud-delivered with on-prem options; integrates into LLM application stacks at runtime; Gandalf community-sourced adversarial data continuously feeding the detection models.
Protections
Real-time block of prompt injection, data leakage, and model manipulation; continuous red teaming surfacing new vulnerability classes pre-deployment; runtime guardrails for LLM outputs; pre-deployment posture assessment for agents and multimodal workflows.
Differentiator
HQ in Zurich became Check Point's Global Center of Excellence for AI Security post-acquisition; Team includes 11 PhDs in AI security research; Gandalf red-teaming community is a uniquely defensible moat — over 1M players have stress-tested LLMs through the platform; Serves Fortune 500 enterprises.
Team & funding
- Founders
- David Haber, Mateo Rojas-Carulla, Václav Volhejn
- Total raised
- $25M
- Investors
- Atomico, Citi Ventures, Dropbox Ventures, redalpine
- Acquired by
- Check Point · Sept 2025 · $300M
Other Runtime & Guardrails companies
AariaSec · ActaClad · ActiveFence · Acuvity · AGAT Software · AgentFox · AI Aramid · AI Prompt Shield · Aiceberg · Aim Security · AIR · Aira Security · See all →
Last updated · Get the “Listed on” badge