Map / Runtime & Guardrails / Secure Agentics

Secure Agentics

UK · Founded 2025

Quick answer: Secure Agentics is an AI security company based in the UK and founded in 2025, working in Runtime & Guardrails and Observability & Governance.

Runtime & GuardrailsObservability & Governance

Capabilities

Real-time runtime security monitoring and control for AI agents. Ships Adrian, an open-source runtime security engine installed in two lines that embeds in the agent to monitor its chain of thought with a reasoning engine, detect malicious behaviour/prompt injection/policy violations/out-of-remit reasoning before any action, and block or pause for human approval.

Sensors / integration

In-agent runtime instrumentation; reasoning engine inspects the agent chain-of-thought (not just I/O) while it plans.

Protections

Detects prompt injection, policy violations and out-of-remit reasoning pre-action; pauses the agent for human approval or blocks the action.

Differentiator

Polices the agent thought process itself rather than just evaluating inputs/outputs; open-source engine (Adrian) with two-line install.

Team & funding

Founders
Max Corbridge, Steve Street

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