Security & Guardrails
26 agents tracked · ranked by trust score · Updated 2026-10-13 11:40 UTC · the three strongest right now:
Grade mix26 agents
4 A3 B14 C5 D
| # | Agent | Trust | Stars | Language |
|---|---|---|---|---|
| 1 | HOL Guard A Listed Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime. | 91.7 | 868 | Python |
| 2 | REA A Listed Reverse engineer anything with agents, from app behavior down to native binaries. | 89.4 | 177.0k | TypeScript |
| 3 | AiSOC A Listed Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue. | 87.2 | 2.4k | Python |
| 4 | DvalinCode A Listed Independent security verification for code written by humans and AI agents. Scan, repair, then prove it — Dvalin runs your project's own checks and issues a Verified Fix Record anyone can re-derive offline. Local-first, policy-bound, MIT. | 84.3 | 118 | TypeScript |
| 5 | Guardrails AI B Listed Adding guardrails to large language models. | 76.4 | 7.5k | Python |
| 6 | NeMo Guardrails B Listed NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. | 72.8 | 7.3k | Python |
| 7 | Garak B Listed the LLM vulnerability scanner | 65.6 | 9.5k | Python |
| 8 | Snyk Agent Scan C Listed Security scanner for AI agents, MCP servers and agent skills. | 63.5 | 3.1k | Python |
| 9 | SkillSpector C Listed Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them. | 62.5 | 20.1k | Python |
| 10 | Deepsec C Listed Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents | 57.5 | 8.1k | TypeScript |
| 11 | PentAGI C Listed Fully autonomous AI Agents system capable of performing complex penetration testing tasks | 55.9 | 27.5k | Go |
| 12 | PentestAgent C Listed PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows. | 55.8 | 3.2k | Python |
| 13 | open-kritt C Listed Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code. | 55.2 | 2.3k | JavaScript |
| 14 | RedAmon C Listed Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what it finds. MCP both ways: plug in any MCP server as a tool, or drive RedAmon from Claude Code or your… | 54.2 | 3.0k | Python |
| 15 | CyberStrike C Listed Open-source AI-powered offensive security harness for automated penetration testing. | 54.0 | 3.1k | TypeScript |
| 16 | LLM Guard C Listed The Security Toolkit for LLM Interactions | 53.3 | 3.2k | Python |
| 17 | Llama Guard C Listed Set of tools to assess and improve LLM security. | 53.1 | 4.4k | Python |
| 18 | Cybermes C Listed Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration. | 52.4 | 934 | Python |
| 19 | pentest-ai C Listed Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself. | 51.3 | 1.7k | Python |
| 20 | Agentic Security C Listed Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪 | 51.1 | 2.0k | Python |
| 21 | Anything Analyzer C Listed 全能协议分析工具：浏览器抓包 + MITM 代理 + 指纹伪装 + AI 分析 + MCP Server 无缝对接 AI Agent/IDE | All-in-one protocol analysis toolkit — built-in browser capture, MITM proxy, JS hooks, fingerprint spoofing, AI analysis & MCP server for agent integration | 50.0 | 3.8k | TypeScript |
| 22 | T3MP3ST D Listed autonomous red teaming platform; multi-agent offensive-security meta-harness | 49.7 | 6.5k | TypeScript |
| 23 | AutoCVE D Listed Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation. | 45.0 | 1.4k | Python |
| 24 | auto-re-agent D Listed Reconstruct and validate C/C++ code from compiled programs with AI. | 44.5 | 2.1k | Python |
| 25 | HexStrike AI D Listed HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security… | 41.6 | 12.7k | Python |
| 26 | Mantis D Listed A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities. | 20.4 | 2.4k | Python |
Grade = trust band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50 — methodology
About Security & Guardrails
HVTracker independently evaluates 26 security & guardrails using daily signals from GitHub, package registries, and security databases. The category is open-source-first, with a limited set of public GitHub-hosted proprietary or source-available comparators when they are important ecosystem reference points. Each agent is scored on activity, adoption, transparency, safety, and identity. The top-ranked security & guardrail is HOL Guard with a trust score of 91.7/100 (Grade A). Other leading projects include REA and AiSOC.