M

multi-agent

Governance framework for multi-agent AI systems in software development

AI-first local-first desktop control room for ai-agent-workflow markdown task boards. Basically AI-controlled kanban board.

NeuroGrid is an open-source, modular AI protocol that enables autonomous multi-agent swarms to collaborate, execute complex tasks, and verify outcomes through structured workflows and specification-driven integrity. It combines decentralized compute, verifiable execution, and persistent knowledge systems to create a scalable intelligence network where agents and humans work together as coordinated teams.

Portable skill for adding a Claude Code lane to OpenAI Symphony + Linear workflows

Open standard for geometric multi-agent AI safety. One decorator. Five-layer defense. 27 C4 cognitive states. 16 AoC failure modes blocked. pip install c4-protocol. Apache 2.0.

Empirical validation of C4 geometric defense against 16 Agents of Chaos. 550 adversarial prompts. 4 defense systems. 96.7% block rate. LLM validation on GPT-4o-mini + Mistral 7B. MIT.

Production AI defense with 7-layer protection: mathematical constraints, object-capability access, distributed O2 consensus, SVETILO ethics. First open-source ThoughtVirus defense. BSL 1.1.

LatticeOS is a modular, human-in-the-loop operating system for governed multi-agent AI orchestration, designed to provide structured execution, deterministic workflows, and full auditability. Built around event-sourced transparency and explicit governance controls, LatticeOS enables intelligent systems where every agent action becomes structured, traceable history while keeping humans in control of all critical decision-making.

AgentFlow-AI est un système d’agent intelligent basé sur une architecture micro-services. Il combine LLM, outils et exécution d’actions pour comprendre les requêtes en langage naturel, planifier et exécuter des actions réelles, et fournir des réponses précises avec contexte.

Bi-temporal CRDT claim substrate with asserter attribution.

Contains the fundamental classes and interfaces that define the basic functionality of the SCOP framework.

A skill and toolkit for running self-improving AI agent teams. Codex or Claude Code orchestrates over Symphony workers with Linear-managed execution. Includes dispatch, review gates, concurrent workers, runbook-driven learning loops, and durable guidance promotion. No auto-merge.

Multi-agent AI travel assistant that coordinates real-time data from Amadeus, OpenWeatherMap, and Gemini to build personalized trip plans via a premium chat interface.

AI autocomplete, helpful chat and knowledgable agent for Godot!

Intelligentes Multi-Agent System für automatisiertes Crypto Trading mit Freqtrade Integration und MCP Protocol

This project is a Social-Network based Multi-Agent System as an Epidemic Model.

A multi-agents in a 2D discrete environment using cognitive agents and Djikstra's algorithm.

A very simple multi-agent system to modelize particles collisions in a 2D discrete environment.