Lists (1)
Stars
Arkana - Your entire malware analysis lab, behind one AI prompt. 250+ MCP tools for binary analysis with Claude Code or other MCP
Fastest measured Qwen3.8-27B config for DGX Spark (GB10): SGLang + NVFP4 + DFlash2, deterministic boots, 50 tok/s greedy median, 148 tok/s at 8 streams, 258 at 32. One command, everything pinned, l…
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models, 7,600+ Ed25519-signed attack skills, 56+ built-in tools, 176+ MCP tools. MITRE ATT&CK,…
Registre public des changements du catalogue fuitesinfos.fr : entrées ajoutées, retirées ou corrigées, avec date, motif et empreinte vérifiable.
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code…
Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.
Uncensored/abliterated Ornith-1.0-35B (AEON Ultimate): 0% refusal, 0 coding-capability loss. BF16 + FP8 for vLLM.
DFlash: Block Diffusion for Flash Speculative Decoding
LLM security testing framework for detecting prompt injection, jailbreaks, and adversarial attacks — 190+ probes, 28 providers, single Go binary
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.
Repository for Dev Container Templates that are managed by Dev Container spec maintainers. See https://github.com/devcontainers/template-starter to create your own!
NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.
The batteries-included agent harness.
Analyses your Java applications for open-source dependencies with known vulnerabilities, using both static analysis and testing to determine code context and usage for greater accuracy. https://ecl…
Catch common Java mistakes as compile-time errors
A modular, stack-agnostic toolkit of security review skills for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
Light, fluffy, and always free - The AWS Local Emulator alternative
universal text transformation, translation, mutation, encoding/decoding, and promptcrafting
The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to verify the security of AI-driven applications.
Démarche d'amélioration cyber, thématique et progressive
Native macOS menu-bar app to control Razer BlackWidow V3 Pro RGB lighting without Synapse — pure IOKit, plus Claude Code hooks that turn the keyboard into a live status light