Memory + Behaviour
Protection for AI Agents

6-layer defence pipeline, behaviour protection, and full dashboard — all running locally. Free and open source. No cloud required.

See Pricing
npm install shieldcortex
pip install shieldcortex

Available on npm and PyPI

Designed for OpenClaw Claude Code Cortex LangChain CrewAI AutoGPT

Iron Dome New

The defence pipeline protects your agent's memory. Iron Dome protects your agent's actions.

$ npx shieldcortex iron-dome activate --profile school

Injection Scanner

40+ patterns across 8 attack categories

Action Gate

Approve, require approval, or block actions

PII Guard

Block protected data from agent output

Instruction Gateway

Only trusted channels can issue commands

Kill Switch

Trigger phrase pauses memory creation instantly

Sub-Agent Control

Restrict spawned agents' capabilities

Explore Iron Dome Read the Docs
🦞 OpenClaw Integration

Every memory your OpenClaw agent saves passes through ShieldCortex. Prompt injection, credential leaks, poisoned context — caught before it reaches storage. Works as a standalone memory system or as a security layer for any memory backend.

Hook Integration

1. npm install -g shieldcortex
2. sudo npx shieldcortex openclaw install
3. npx shieldcortex config --cloud-api-key <key> --cloud-enable

Scans memory writes via session hooks. Auto-memory now opt-in with smart deduplication.

Real-time Plugin

New

Scans every LLM input for threats and auto-extracts memories from outputs. Fire-and-forget — never blocks your agent.

Auto-installed by openclaw install — no manual config needed.

Requires OpenClaw v2026.2.15+. Details →

Works on macOS, Linux (including headless servers), and Windows. Onboarding a team member? Just give them an API key — no signup needed.

Team setup guide →

AI Agents Have Three Problems

Most solutions fix one. ShieldCortex solves all three.

😵

Amnesia

Your agent forgets everything between sessions. No context. No learning. Starting from zero every time.

🎯

Memory Vulnerability

The moment you add memory, you create an attack surface. Memory poisoning. Prompt injection. Credential harvesting.

🤖

Behaviour Vulnerability

Agents can be tricked into executing harmful actions via prompt injection. No guardrails on what they do, only what they remember.

ShieldCortex = Memory + Security + Behaviour Protection

Stop choosing. Get all three.

What You Get

Full protection for free. Pro licence for custom rules. Team licence for cloud sync.

🛡️

Local Protection

npm package — free and open source

  • Memory Firewall — Block injection attacks in real time
  • Trust Scoring — Filter by source reliability
  • Anomaly Detection — Behavioural scoring over time
  • MCP Tools — Native support for Claude Code, OpenClaw
  • Universal Memory Bridge — Guard any memory backend with the defence pipeline
  • 6-Layer Defence Pipeline — Sanitise, detect, analyse, validate, score, credential scan
  • Security Audit — A-F grading, CVE detection, CI/CD integration via GitHub Action
  • Iron Dome — Behaviour protection: injection scanning, action gating, PII guard

Context Preservation

  • Pre-Compaction Extraction — Auto-saves decisions, fixes, and learnings before context is lost
  • Session Continuity — Auto-loads project context at session start, extracts on exit
  • Salience Scoring — Prioritises what matters, lets noise decay naturally
  • Memory Consolidation — Promotes short-term to long-term memory, like brain sleep
⚡

Pro + Team

Licence key — from £29/mo

Pro Features

  • Custom Injection Patterns — Up to 50 regex rules for domain-specific threats
  • Custom Iron Dome Policies — Tailor behaviour controls to your use case
  • Audit Export — JSON/CSV export of your defence logs
  • Skill Scanner Deep Mode — Multi-file semantic analysis

Team Features

  • Cloud Audit Sync — Centralised logs across all devices
  • Team Management — Invite members, shared custom patterns
Compare plans →

Your Agent Never Forgets

AI agents lose context during compaction, between sessions, and when conversations get long. ShieldCortex intercepts at every point where memory is lost.

🧠

Before Compaction

Auto-extracts decisions, fixes, and learnings before they get compressed away.

🔄

Session Start

Loads your highest-priority memories automatically. No blank slate.

⚖️

Smart Priority

Salience scoring keeps architecture decisions and bug fixes; lets noise decay naturally.

💤

Consolidation

Promotes short-term to long-term memory and merges related items. Like brain sleep.

Get Started in Minutes

Choose your path.

🦞

OpenClaw Users

1.
sudo npx shieldcortex openclaw install

Install the OpenClaw hook

2.
openclaw gateway restart

Activate the real-time plugin

3.
Done. Every memory is now protected.
🐍

Python

New
1.
pip install shieldcortex

LangChain/CrewAI extras available

2.
Scan content before it reaches memory

Local scanning — no API key needed

3.
Done. Works with LangChain, CrewAI, and REST APIs.
See Python docs →
📦

Node.js

1.
npm install shieldcortex

Add to your project

2.
npx shieldcortex setup

Configure your agent integration

3.
npx shieldcortex --dashboard

View threats, audit log, and brain visualisation

Node.js 18+ or Python 3.9+ — macOS, Linux & Windows

Start Protecting Your Agents

Install free. Upgrade locally with a licence key.

See Pricing
npm install shieldcortex
pip install shieldcortex