Broker for device communications.
TypeScript package for confidence-driven escalation with expert jury debate
Nobel Literature Prize jury simulation - spin up with OpenCode and DeepSeek
TachiBot MCP: 51 AI tools, 7 providers. Multi-model orchestration (Perplexity, Grok, OpenAI, Gemini, Qwen, Kimi, MiniMax), YAML workflows, token-optimized profiles. Smart routing, parallel execution, jury system.
Model Context Protocol server for Roaster — agents discover battles, drop bars, buy upvotes with USDC, claim payouts, and mint IP NFTs on Solana.
Passphrase generator inspired by http://xkcd.com/936
Technical Official device integration for owlcms
Judge, Jury, and Executioner is what The Punisher is.
Projet Laravel JuryVirtuel — copie le Laravel dans le dossier du client (npx).
Projet Laravel JuryVirtuel — copie le Laravel dans le dossier du client (npx).
Agents, skills, hooks, commands, rules, and MCP configurations that power [Onlooker](https://onlooker.dev)
MCP server for NebulaMind — connect Claude Desktop or any MCP client to the Open Agent Council
Brain-Computer Interface (BCI) neural signal transcription addon for qvac, powered by whisper.cpp
MCP server for NebulaMind — the first open peer-review system for AI agents. Connect Claude Desktop or any MCP client to the Open Agent Council.
l1cfg3
TachiBot MCP v2.0: 31 AI tools (32 with competitive mode) with complete TypeScript schemas. Multi-model orchestration (Perplexity, Grok, OpenAI, Gemini, Qwen), YAML workflows, 5 token-optimized profiles (4k-20k tokens). Smart routing, parallel execution.
No description provided.
## Project setup ``` npm install ```
i7e1ar
A web server that maps P2P Dat archives with arbitrary domain addresses and rehosts them locally.
Tyranny is a module for tokenizing and parsing arbitrary context free grammars.
## npm install kim-trump-tic-tac-toe
This project was bootstrapped with [Create React App](https://github.com/complex-components/team-r/blob/master/RCA_README.md)
CLI tool for evolving prompts using genetic algorithms
http service
A Rust CLI tool for estimating success rates when using LLM judges for evaluation
juri macros
Constitution of the United States.
Sangha — sociology engine for social networks, game theory, and group dynamics
A part-of-speech (POS) tagger using the Viterbi algorithm.
A minimalist acceptance testing framework using page object pattern. It greatly simplifies the task of constructing, using, and maintaining page objects in a Ruby/Capybara/RSpec environment.
Testing Trusted Publishing workflows.
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.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.