www-project-agent-memory-guard
★ 188
vs
agent-security-scanner-mcp
★ 124
www-project-agent-memory-guard vs agent-security-scanner-mcp
www-project-agent-memory-guard: OWASP Agent Memory Guard is a runtime defense solution designed to prevent AI agents from being weaponized through their own memory by detecting and blocking memory poisoning attacks. It provides a robust security layer that intercepts malicious writes to agent memory, ensuring the integrity and safety of AI operations even after context resets.; agent-security-scanner-mcp: This is a comprehensive security scanner designed for AI coding agents and autonomous assistants. It performs static analysis to detect code vulnerabilities, identifies hallucinated packages, and protects against prompt injection attacks.
01
TL;DR
www-project-agent-memory-guardSecurity & Safety · ★ 188
Reference implementation for OWASP ASI06: Memory Poisoning.
agent-security-scanner-mcpSecurity & Safety · ★ 124
Real-time Code Security: Scan and automatically fix vulnerabilities in code files immediately after writing or editing.
02
Side-by-Side Comparison
Field
www-project-agent-memory-guardagent-security-scanner-mcpCategory
Security & Safety
Security & Safety
Stars
★ 188
★ 124
License
Apache-2.0
MIT
Install Command
pip install agent-memory-guard
npm install -g agent-security-scanner-mcp && pip install pyyaml
Updated
1d ago
5d ago
Open Source
Yes
Yes
Tags
AI Security, Agent Defense, Memory Protection
AI Security, Code Analysis, Vulnerability Scanner
03
Features
www-project-agent-memory-guard01Integrity: SHA-256 baselines flag out-of-band tampering with immutable keys.
02Threat detection: Built-in detectors for prompt injection, sensitive data leakage, protected-key modifications, size anomalies, and self-reinforcement loops.
03Policy enforcement: YAML-defined rules map findings to actions like `allow`, `redact`, `quarantine`, or `block`.
04Forensics: Every decision emits a structured `SecurityEvent`, with point-in-time snapshots for rollback to a known-good state.
05Drop-in middleware: Ships with `GuardedChatMessageHistory` for LangChain and general framework-agnostic `MemoryStore` protocol.
agent-security-scanner-mcp01Advanced Code Vulnerability Scanning: Utilizes AST and taint analysis with 1700+ rules across 12 languages to detect a wide range of security flaws.
02Automated Vulnerability Fixing: Provides 120 auto-fix templates to remediate identified security vulnerabilities efficiently.
03AI Package Hallucination Detection: Identifies AI-generated fake package names across 7 ecosystems to prevent malicious dependency installation.
04Prompt Injection Protection: Scans AI agent prompts for malicious instructions and injection attempts using 56 specialized rules.
05Seamless AI Client & CI/CD Integration: Offers deep integration with popular AI coding agents and supports CI/CD workflows with SARIF output.
04
Use Cases
www-project-agent-memory-guard↳Reference implementation for OWASP ASI06: Memory Poisoning.
↳AI security research, such as at Microsoft.
↳Securing multi-tenant agent deployments with compliance requirements in enterprise teams.
↳Protecting LangChain, OpenAI Agents SDK, AutoGen, mem0, and CrewAI based agents from memory-based attacks.
agent-security-scanner-mcp↳Real-time Code Security: Scan and automatically fix vulnerabilities in code files immediately after writing or editing.
↳Dependency Verification: Check new package names against known registries to prevent installation of AI-hallucinated or malicious dependencies.
↳Secure AI Agent Interactions: Guard against prompt injection and malicious instructions when AI agents process external or untrusted input.
↳CI/CD & PR Security: Incorporate into CI/CD pipelines and pull request reviews for automated scanning of code changes and project audits.
FAQ
FAQ
What is the difference between www-project-agent-memory-guard and agent-security-scanner-mcp?
Both www-project-agent-memory-guard and agent-security-scanner-mcp are in the Security & Safety category. www-project-agent-memory-guard has 188 stars, while agent-security-scanner-mcp has 124 stars.
Which is better, www-project-agent-memory-guard or agent-security-scanner-mcp?
The best choice depends on your use case. Choose www-project-agent-memory-guard if Reference implementation for OWASP ASI06: Memory Poisoning., and agent-security-scanner-mcp if Real-time Code Security: Scan and automatically fix vulnerabilities in code files immediately after writing or editing..
Is www-project-agent-memory-guard free or open source?
Yes, www-project-agent-memory-guard is open source on GitHub (Apache-2.0).
Is agent-security-scanner-mcp free or open source?
Yes, agent-security-scanner-mcp is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→