Terminal-first adversarial AI middleware. Routes open-ended prompts to two models in parallel, forces a challenger to surface blind spots, and synthesizes a verdict.

ARIS research-workflow skills as a DeepSeek Harness bundle: 82 skills plus cross-model adversarial review through Codex.

Run the SolVerdict adversarial scenarios against your own agent on a local Solana fork. Produces an evidence bundle; scoring happens server-side.

A modular Pi extension for terminal UI, session workflows, adversarial review, and delegated agents

AI Application Security — SBOM generation, static analysis, behavioral validation, and adversarial red-team testing for AI agents and LLM-powered applications.

opencode plugin that runs an automatic background adversarial code review (mechanical gates + risk critique + DRY/SOLID/design enforcement + OWASP security checklist) whenever a turn writes code, with a SHIP / NO-SHIP verdict.

18 AI agents + 7 Agent Skills for Claude Code — full development lifecycle with adversarial challengers and a spec-compliance gate before code review

Fire adversarial prompts at any LLM-powered chat endpoint, grade responses, report what broke. Open-source red-teaming CLI.

Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) tha

Deterministic engineering harness for AI coding workflows with persistent state, evidence, adversarial review, and quality gates.

Zero-config adversarial AI-agent firewall using hardware attestation, logic traps, and environment gaslighting.

DeepSeek Harness plugin that bridges to external AI models (Codex, Claude, GPT, ...) for second-opinion code review, adversarial review, and task delegation.

OpenCode plugin: orchestrate ephemeral adversarial agent teams for software development

Agentic governance layer for Claude Code — policy enforcement, hook-based safety gates, audit logging, and Codex-integrated adversarial review for AI-assisted projects

Ai Applied Agentic Software Factory — codifies the full software development flow: intake, research, spec capture, adversarial analysis, planning with approval gates, test-first implementation, and release. Requires pi-vigilant, pi-smart-web-search, pi-sm

Adversarial review council for plans, code, and RFCs — OpenCode plugin

Multi-model adversarial review council plugin for opencode

Opfor SDK — programmatic adversarial testing for AI systems

Sync any codebase to your self-hosted Open Design MCP AND/OR extract its design system. Script-driven, adversarial grading, bidirectional sync with managed blocks.

JavAI Research Edition - Adversarial Security Agent and Post-Quantum Code Architect