Security plugin for OpenCode with pattern detection and LLM adversary mode
MITRE ATT&CK adversary TTPs (STIX bundles)
MCP server for MITRE CALDERA adversary emulation platform API (read-only)
MCP server for Atomic Red Team adversary emulation tests
regex verification circuits in circom for common regexes, generated with the compiler in [zk-regex](https://github.com/zkemail/zk-regex/tree/main).
OpenCode plugin: orchestrate ephemeral adversarial agent teams for software development
Like Set, but without methods for mutation
Multi-agent adversarial code review for any coding agent. Single model, three lenses, two rounds. Ships as both a CLI and a Claude Code Skill.
Economic attack simulation framework for Solana DeFi — oracle manipulation, flash loans, MEV sandwiches, governance griefing. Runs YAML scenarios + genetic-fuzz parameter search, exits non-zero on invariant breach.
A webassembly client which can be used to interact with the the Nym privacy platform. Wasm is used for Sphinx packet generation.
SPD (Secure Packaged Data) — a compressed, post-quantum-hardened encrypted data format for Node.js. Supports chunked internet transfer, large-file streaming (>2 GB), Argon2id key derivation, XChaCha20-Poly1305 AEAD, and HMAC-SHA3-512 authentication.
A webassembly client which can be used to interact with the the Nym privacy platform. Wasm is used for Sphinx packet generation.
This Obsidian.md plugin aims to be a comprehensive set of tools for Daggerheart game masters.
Seamless dynamic workflow orchestration for OpenCode. Install, setup, use inside OpenCode.
Command-line interface for the Recall local knowledge platform
Complete MCP server for MITRE ATT&CK threat intelligence framework with 50+ tools
H3RETIK SOTA red teaming TUI bootstrap CLI
kehgds
Universal skill library for Claude, ChatGPT, Cursor, Gemini, and VS Code. Install once globally, use everywhere.
mocha configuration for eslint
An immersive CLI game inspired by the TV series Person of Interest.
jasmine configuration for eslint
> **Private machine-to-machine payments for AI agents.** > Zero on-chain trace · No KYC · No credit cards · Instant USDC settlement
JSON Template HTML Extension Library Framework
Adversarial property-based testing for Rust.
Adversarial (Red/Blue) agent pairing for VEX
Adversarial robustness primitives for OxiCUDA: FGSM, PGD, MIM, CW, AutoPGD attacks; TRADES, MART, randomized smoothing, certified bounds — pure Rust, zero CUDA SDK dependency.
Rust adversarial search library
Procedural macros for the adversary crate.
Adversarial review for Organism — challenges, skeptics, governance signals
High-level training, benchmarking, and adversarial training infrastructure for AxonML
Deterministic spectral residual inference demonstrator for swarm interaction networks
Adversarial agent security testing tool
AXON — the formal cognitive language: a deterministic, proof-carrying AI runtime. Native Rust lexer/parser/type-checker/IR generator (re-exported from axon-frontend) plus the runtime: typed channels (π-calculus mobility, capability extrusion), algebraic effects via Free Monad CPS handlers, lease kernel + reconcile loop, the Epistemic Security Kernel, Trust Types, Proof-Carrying Code (independently verifiable proof objects), and the closed-catalog extension mechanism. Crate publishes as `axon-lang`; library import is `use axon::*` so existing call sites keep working unchanged.
LLM-powered fuzzing assistant for Solidity smart contracts — generates, runs, and iterates invariant tests with Foundry
Adversarial Testing Harness for Large Language Models
Fleet pipeline validation: tests, lint, security scan, adversarial LLM review
LAI is a promising post-quantum cryptosystem based on isogenies of elliptic curves over lemniscate lattices, offering resistance against quantum-capable adversaries.
Models an adaptive immune system for AI agents. Detects adversarial inputs, builds learned immunity through antigen/antibody pattern matching, and provides graduated immune responses from tolerance to full rejection.