secureagentics

Adrian

Runtime security for AI agents: watches actions AND reasoning traces to catch prompt injection, tool poisoning and out-of-remit behavior — blocking before the action lands. SDKs + Claude Code plugin.

460 85 Python Apache-2.0updated 4 days ago

security agents

View on GitHubDispute this mapping →

Curator's take

The interesting bet is judging reasoning traces, not just tool calls, against a working model of the agent's remit — the OpenAI/DeepMind-cited combo that catches what injection-trained classifiers miss. Know the deployment shape: the quickstart routes your agent's actions AND thoughts through their managed dashboard; self-hosting exists but is the longer path. Young (★460) and a startup's wedge product — run audit mode first and measure false positives on your own traffic before trusting block mode in production.

Mapped by ShipWithAI editors · links verified

README.md

Agent attacks slip past static analysis and network monitoring.

Adrian catches them at runtime, by watching what the agent actually does (its actions and its reasoning) and stepping in before it acts. Open source, free forever.

+35% detection accuracy · 4x more nuanced attacks caught vs behaviour-only monitoring (OpenAI & DeepMind research)

⭐ If you think agents need a runtime security layer, star the repo. It is how new people find Adrian, and how we know to keep building it in the open.

Adrian is an open-source, AARM-aligned runtime security monitoring and control engine for AI agents. It analyses both agent activity logs (tool calls, actions, outputs) and reasoning traces to detect malicious, misaligned, or out-of-remit behaviour, and optionally intervene in-flight. SDKs are available for Python (LangChain) and TypeScript (sdk/typescript/README.md), plus a native Claude Code plugin that secures every tool call from your terminal.

🆕 Claude Code plugin - now live. Drop Adrian into Claude Code and every tool call is classified in real time, with risky actions blocked or held for your approval right in the terminal. No code changes: install with /plugin marketplace add secureagentics/Adrian then /adrian-init. Full guide: integrations/claude-code/README.md.

Documentation • Dashboard • Discord • LinkedIn

▶️ See it in action: Adrian catches an agent going out-of-remit in real time and steps in before the action lands.

https://github.com/user-attachments/assets/ba50e6e4-fe3e-47b2-aa69-2902e1ef2924

^{New to Adrian? Check out the Launch Video.}

Why Adrian is different

Most agent monitoring stops at activity logs: APIs, MCP, DB interactions, tool calls, etc. Adrian enhances this by also analysing the agent's reasoning: understanding why it took an action, under what context, and what it is planning on doing next. Combining behaviour and reasoning analysis like this is exactly what the [Open

Continue your stack

What teams reach for next — and why each earns a place beside Adrian. Ranked by curator confidence.

Pairs well with

garak

NVIDIA's LLM vulnerability scanner: nmap-style probing for jailbreaks, prompt injection, data leakage, toxicity and hallucination across dozens of model endpoints.

Why it fitsTwo halves of agent security: garak probes for jailbreaks and injection weaknesses before you ship; Adrian watches the live agent and intervenes when an attack actually lands.

Alternative to See all + compare →

Guardrails

NVIDIA's programmable guardrails for LLM apps: input, output, dialog and retrieval rails defined in Colang, wrapping any model or LangChain runnable.

Why it fitsBoth police live LLM behavior, opposite philosophies: NeMo Guardrails executes rails you wrote in Colang — you enumerate the policy; Adrian infers the agent's remit and flags deviations, reasoning traces included.