updated 2026-08-14 16:04 UTC

Security & Guardrails

19 agents tracked · Open-source-first, with limited public GitHub comparators · Ranked by trust score · Updated 2026-08-14 16:04 UTC

HVTracker independently evaluates 19 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 DvalinCode with a trust score of 85.4/100 (Grade A). Other leading projects include Guardrails AI and NeMo Guardrails.

19
Agents
52
Avg Trust
105.3k
Total Stars
2
Grade A
# Agent Trust Stars Language
1 DvalinCode A Listed Approvable, local-first AI coding agent for regulated teams: policy controls, governed MCP, evidence packs, audit trails 85.4 112 TypeScript
2 Guardrails AI A Listed Adding guardrails to large language models. 83.3 7.3k Python
3 NeMo Guardrails B Listed NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. 72.0 7.0k Python
4 REA B Listed Reverse engineer anything with agents, from app behavior down to native binaries. 71.2 308 TypeScript
5 Snyk Agent Scan C Listed Security scanner for AI agents, MCP servers and agent skills. 64.0 2.9k Python
6 PentAGI C Listed Fully autonomous AI Agents system capable of performing complex penetration testing tasks 63.7 21.8k Go
7 SkillSpector C Listed Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data 63.3 14.6k Python
8 Deepsec C Listed Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents 59.9 7.5k TypeScript
9 Garak C Listed the LLM vulnerability scanner 58.6 8.8k Python
10 PentestAgent C Listed PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration t 56.6 2.9k Python
11 LLM Guard C Listed The Security Toolkit for LLM Interactions 55.0 3.2k Python
12 Llama Guard C Listed Set of tools to assess and improve LLM security. 52.6 4.3k Python
13 Agentic Security D Listed Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪 49.4 2.0k Python
14 HexStrike AI D Listed HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ 46.8 11.0k Python
15 T3MP3ST D Listed autonomous red teaming platform; multi-agent offensive-security meta-harness 24.9 5.6k TypeScript
16 CyberStrike D Listed Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models, 7,600+ Ed 24.4 1.8k TypeScript
17 pentest-ai D Listed Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof caps 19.7 1.6k Python
18 auto-re-agent D Listed Open-source AI reverse-engineering agent using Ghidra and LLMs to reconstruct and validate C/C++ functions from binaries 19.1 1.3k Python
19 AutoCVE D Listed Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generatio 18.9 1.3k Python

Grade = trust band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50 — methodology