Stars
Public source of the Dreadnode capabilities in app.dreadnode.io — agents, tools, skills, MCP servers, and workers.
Use your Kimi Code (Moonshot) subscription in OpenCode via OAuth device flow
GitHub Action to alert on security patches before the CVE drops.
CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.
Framework for evaluating and improving agents
Remote service-staging tool built on Impacket, designed for BOF-style lateral movement workflows that lets you upload custom service loaders, set descriptions, and run them on demand.
The Foundation AI Testing Hub (FAITH) is a benchmarking tool used to assess LLMs competency on (cybersecurity) knowledge/tasks.
AI agent for autonomous cyber operations
Harnessing AI to Disrupt and Evaluate Security (HADES)
A Model Context Protocol (MCP) server to converse with data in Bloodhound
Build Real-Time Knowledge Graphs for AI Agents
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
A collaborative, multi-platform, red teaming framework
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
⚡ A Fast, Extensible Progress Bar for Python and CLI
An automated Adversary Emulation lab with terraform and MCP server. Build Caldera techniques and operations assisted with LLMs. Built for IaC stability, consistency, and speed.
Python client for Qdrant vector search engine
Open Adversarial Exposure Validation Platform
A comprehensive local Linux Privilege-Escalation Benchmark