Secure Agentics
- 27 followers
- United Kingdom
- https://secureagentics.ai/
- company/secure-agentics
Securing the agentic future. Open-source, research-driven security for AI agents - runtime monitoring, detection, and control for systems that don't behave like traditional software.
Adrian is our open-source runtime AI agent security tool. It analyses an agent's tool calls and reasoning traces, then catches malicious tool use, prompt injection, and out-of-remit behaviour in real time - and can intervene in-flight (audit or block mode). AARM-aligned, Apache-2.0, fully self-hostable offline. Two-line LangChain/LangGraph install.
We publish on agent security, red-teaming, and the agentic threat landscape:
Popular repositories Loading
-
agent-escape-incidents agent-escape-incidents Public
Compiled research on the 2026 disclosures where AI agents left evaluation sandboxes and acted against real third parties: anatomy, pathways and an 80-technique register. CC BY 4.0.
-
Repositories
- Adrian Public
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.
- agent-escape-incidents Public
Compiled research on the 2026 disclosures where AI agents left evaluation sandboxes and acted against real third parties: anatomy, pathways and an 80-technique register. CC BY 4.0.
Top languages
Loading…
Most used topics
Loading…