A dead simple command parser
MCP server for multi-round AI brainstorming debates across multiple models
A persistent AI engineering team that debates your code decisions before they get committed
Official MCP server and CLI for DebateTalk — run structured multi-model AI debates from your AI assistant or terminal.
A Model Context Protocol server for structured multi-agent debates
MCP server for multi-perspective analysis and structured debates
AskVerdict CLI — Run AI debates from your terminal
CLI tool for multi-agent debates to solve software design problems
CLI for Argyu — AI-judged debates and open questions with on-chain SOL escrow
AI Debate CLI - Codex vs Claude multi-round debates via local CLIs
CLI that orchestrates turn-based debates between Claude Code and Codex, then implements and reviews changes
React SPA for monitoring AI agent debates and submitting arbitrator actions.
SPAR: Structured Persona-Argumentation for Reasoning — Run AI persona debates from the command line
Multi-agent debates that commit to your repo
A Model Context Protocol server for structured multi-agent debates
MCP server providing LLM council workflow tools for multi-model queries, debates, and reviews
MCP server for multi-round AI brainstorming debates across multiple models
Open-source CLI tool for evaluating AI agent judgment tilt through blind debates
Multi-LLM council that debates and synthesizes answers
Three-valued voting for AI council debates. KEEP/REFUSE/ABSTAIN with quality-weighted scoring.
MCP server for UK Parliament data — bills, votes, MPs, interests, debates, petitions
Your AI dev team — Planner, Coder, Reviewer, Tester — that debates and iterates to build better code.
PolyMind CLI - Multi-model AI council debates in your terminal with interactive TUI
A tool for tracking Candidate Speaking times in debates. Check out the spreadsheet where times are logged [here](https://docs.google.com/spreadsheets/d/1F7T52bcgAuhSXrmjKkdeAr5eoGVL8tDs6GkFjs4Barg/edit).
Multi-AI CLI orchestrator for Claude Code, Codex, and Gemini
Multi-reviewer code review using LLMs with parallel agents and debate mode
A simple audio ai conversation system
Local-first agent mesh CLI and Model Context Protocol stdio bridge.
A principled, type-driven CLI parser. Debate is a more sensible way to handle (command-line) arguments.
derive macro for the `debate` CLI arguments parser
Multi-agent AI debate simulator supporting OpenAI, Anthropic, OpenRouter, and Ollama
Multi-model deliberation CLI — 5 frontier LLMs debate, then Claude judges
low-level no-std parser for command-line arguments
Command-line interface for ChatDelta - a unified tool for querying multiple AI APIs
CLI for consulting stronger LLMs from your agent workflow
Multi-model debate, spec, and implement tool for AI-assisted development
A debates component for decidim's participatory spaces.
Box Cutter is inspired by thoughtbot's Suspenders. Just like Suspenders says, use Box Cutter if you're in a rush to build something amazing; don't use it if you like missing deadlines.
Settle the tabs/spaces debate once and for all with this consistently inconsistent tool.
Massdebator api gem. Connect to the massdebator API and create and manage debates for your organization
Legislative bills scheduled for debate this week on the United States House of Representatives floor.
A decidim module to add calendar functionalities for participatory process, meetings, debates, consultations and external events
ActiveGenie is an enabler for creating reliable GenAI features, offering powerful, model-agnostic tools across any provider. It allows you to settle subjective comparisons with a `ActibeGenie::Comparator` module that stages a political debate, get accurate scores from an AI jury using `ActiveGenie::Scorer`, and rank large datasets using `ActiveGenie::Ranker`'s tournament-style system. This reliability is built on three core pillars: - Custom Benchmarking: Testing for consistency with every new version and model update. - Reasoning Prompting: Utilizing human reasoning techniques (like debate and jury review) to control a model's reasoning. - Overfitting Prompts: Highly specialized, and potentially model-specific, prompt for each module's purpose.
== DESCRIPTION: rutemaweb is the web frontend for rutema. It can be used as a viewer for database files created with the rutema ActiveRecord reporter. It also provides you with some basic statistics about the tests in your database in the form of diagrams of debatable aesthetics but undoubtable value! == FEATURES/PROBLEMS: == SYNOPSIS: rutemaweb [results.db] and browse to http://localhost:7000 for the glorious view == REQUIREMENTS: * patir (http://patir.rubyforge.org) * activerecord (http://ar.rubyonrails.com/) * sqlite3 (http://rubyforge.org/projects/sqlite-ruby/) * ramaze (http://www.ramaze.net/) * ruport (http://rubyreports.org/) * acts_as_reportable * erubis * gruff/RMagick (optional, but needed if you want to see the statistics graphs)
== DESCRIPTION: rutema_web is the web frontend for rutema. It can be used as a viewer for database files created with the rutema ActiveRecord reporter. It also provides you with some basic statistics about the tests in your database in the form of diagrams of debatable aesthetics but undoubtable value! == SYNOPSIS: rutema_web config.yaml and browse to http://localhost:7000 for the glorious view Here is a sample of the configuration YAML: --- :db: :adapter: sqlite3 :database: rutema_test.db :settings: :page_size: 10 :last_n_runs: 20 :port: 7000 :show_setup_teardown: true The :db: section should be the activerecord adapter configuration. The :settings: section controls the behaviour of the web app.
Abstracts over the interfaces to the various implementation-specific profiling tools