Position-driven adversarial debate CLI — host supplies opposing stances, arena runs the debate across local model CLIs (Claude, Codex, Gemini, OpenAI, Kimi).

Multi-model LLM Council for adversarial debate, cross-validation, and synthesized decision-making via pi-teams

Multi-model LLM Council for adversarial debate, cross-validation, and synthesized decision-making via pi-teams

Multi-model deliberation engine for high-stakes decisions. Adversarial debate, anonymized peer review, structured synthesis.

SOTA NPM module for agentic processes using local or cloud LLMs.

Multi-agent roundtable debate plugin for OpenCode. Real cross-examination, quality-gated consensus, and dissent tracking.

Multi-model AI verification with adversarial critique. No AI can verify itself — so they verify each other.

Adversarial debate pipeline for code review — Critic, Tester, and Advocate agents debate changes while a Judge produces an actionable checklist

ESRGAN Default Model for UpscalerJS. Upscale images and increase image resolution with AI using Javascript

Adversarial, ship/no-ship code review of a git diff or branch — runs against any LLM (API or local CLI agent) and returns structured findings

Producer-side source, extraction, candidate, and review contracts for projecting verified claims into Surface.

An MCP server that bridges to multiple OpenAI-compatible LLMs - your AI rubber duck debugging panel

<div align="center">

Run structured multi-model debates in OpenCode.

MCP server for multi-round AI brainstorming debates across multiple models

ESRGAN Slim Model for UpscalerJS. Upscale images and increase image resolution with AI using Javascript

AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get

Multi-agent plan-debate room served over MCP — chat agents from any vendor (Claude Code, Codex, Cursor, ...) join a shared room, debate a plan through distinct lenses, and a Speaker moderates and produces a verdict.

AI coding framework — composable skills for planning, executing, verifying, and reviewing code with any LLM provider. Works as Claude Code commands, Codex tasks, or programmatically.

Element React module for WordPress.