Havuz

Cairn, hedef ve başlangıç durumu verildiğinde ortak bir durum grafiği üzerinden keşif görevleri yürüten, ilk olarak otonom penetration testing alanında denenmiş bir AI search engine’dir.

Neden yükseliyor · 162 günlük bir repoda 3.082 yıldız dikkat çekiyor; README, Tencent Cloud Hackathon’daki 54/54 başarı iddiasını ve 610 takım arasındaki sonucunu öne çıkarıyor. Bu sonuç proje tarafından raporlanmış; bağımsız doğrulaması verilen bilgilerde yok. Son 28 günde 1 commit ve 1 farklı yazar bulunması, yıldız ilgisinin güncel geliştirme temposuyla aynı ölçüde desteklenmediğini gösteriyor.

🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomo

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for

A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-tea

NeMo Helix: Make the agents you ship faster, more accurate, and safer.

Curated archive of jailbreak and prompt-injection experiments for AI model robustness research, red-teaming, and defensive evaluation.

rook by TestMu AI: Agent Assurance from the terminal. Test how your AI agents actually behave across workflows, tools, and actions, and catc

Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI

Adversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression tes

DiagSafe: diagnostic LLM safety benchmark with prompt-level rubrics (3,489 bilingual prompts, 84-label taxonomy)

Enterprise Zero-Trust AI Security & Governance Gateway: Real-Time Prompt Injection Defense, Action Scoping, HITL Approvals, Post-Quantum Mer

Red team vs blue team benchmark for scientific paper verification. Plant defects into open access biomedical papers, build gates to catch th

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming)

The elite design intelligence layer for AI agents, synthesized from 10+ legendary design books. It primes your AI with the collective strate

Myrtia — agent-native red teaming for LLMs and AI agents: a deliberating council of attacker models (propose, cross-critique, Borda vote, ch

pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents

Open database of system prompts extracted from frontier LLMs using JustAsk

Red-team your RAG pipeline for prompt injection, source-document leakage, and cross-document smuggling, in CI. The gap between RAG eval (RAG

Agent trace and tool-use safety evaluation lab.

🛡 Official AI Security Tool module for CVE-2026-75604 (Next.js Windows Unauthenticated Remote Code Execution) with safe in-app execution, de

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.

Phoenix-native LLM evaluation, prompt testing, model comparison, red teaming, and observability for Elixir

Governed Postgres access for AI assistants: an MCP gateway with OAuth 2.1 and OIDC login, one Postgres role per person, database-enforced re

Safety benchmark for personal AI agents under realistic prompt injection. 120 test cases across 5 professional domains, 3 injection vectors,

A platform for running human-centered red teaming evaluations on AI models and systems.

Empowers the AI to perform penetration testing, vulnerability assessment, reconnaissance, and security reporting — all through natural langu

Harness-driven terminal AI agent for authorized security assessment, with TUI, headless automation, persistent context, 150 built-in skill

DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Ten