security-research

Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.

AI-native IDE with agentic workflows, iPhone emulation on Windows/Linux, PyTorch ML Studio, and ROCm-optimized local AI. Built for security researchers and cross-platform developers.

Remove invisible AI watermarks (SynthID, StableSignature, TreeRing) and strip AI metadata from images. Open-source CLI & Python toolkit.

冷咖啡 ColdBrew 四合一破甲正式版 — GPT-5.6 / Claude / Grok 4.6 / DeepSeek v4 Pro 一键部署 · 启动 · 恢复 · 打包发布 | QQ 群 1057540028 / 1077074552

Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Opus 4.7. Eight-phase sink-guided pipeline, ~$1/run, OSS self-scan and coordinated disclosure.

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