Multi-agent AI framework where LLMs debate each other to verify claims. Bayesian reasoning, adversarial evidence, calibrated verdicts & full audit trails. Works with GPT-4, Claude, Gemini & local models via Ollama.
# ARGUS **Agentic Research & Governance Unified System** *A debate-native, multi-agent AI framework for evidence-based reasoning with structured argumentation, decision-theoretic planning, and full provenance tracking.* [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) [](https://pypi.org/project/argus-debate-ai/4.5.0/) [](https://github.com/psf/black) [](https://mypy.readthedocs.io/) [](https://github.com/Ronit26Mehta/argus-ai-debate#tool-integrations-50) [](https://github.com/Ronit26Mehta/argus-ai-debate#llm-providers-27) --- ## Table of Contents - [Overview](#overview) - [Key Innovations](#key-innovations) - [Features](#features) - [Installation](#installation) - [Quick Start](#quick-start) - [LLM Providers](#llm-providers) - [Tool Integrations (50+)](#tool-integrations-50) - [OpenAPI REST Integration](#openapi-rest-integration) - [Context Caching](#context-caching) - [Context Compression](#context-compression) - [Debate Visualization](#debate-visualization) - [External Connectors](#external-connectors) - [Visualization & Plotting](#visualization--plotting) - [Argus Terminal (TUI)](#argus-terminal-tui) - [Argus-Viz (Streamlit Sandbox)](#argus-viz-streamlit-sandbox) - [CRUX-Viz (CRUX Protocol Sandbox)](#crux-viz-crux-protocol-sandbox) - [ARISTOTLE Chat Interface](#aristotle-chat-interface) - [CRUX Protocol](#crux-protocol) - [Command Line Interface](#command-line-interface) - [Configuration](#configuration) - [Architecture](#architecture
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.