affaan-m/ECC
ECC is a harness-native operator system designed for agentic AI work, providing a comprehensive solution with skills, memory optimization, security, and research-first development across multiple A...
Awesome AI Agents › Multi-Agent Frameworks
metauto-ai/NLSOM
The project "Natural Language-Based Societies of Mind (NLSOM)" introduces a novel concept inspired by Marvin Minsky's "Society of Mind" and Schmidhuber's "Learning to Think." It envisions a system where diverse agents, including large language models (LLMs), neural network-based experts, APIs, and role-players, communicate exclusively through natural language to collaboratively solve complex tasks. This collaboration is termed "Mindstorm," a process where agents interview each other to leverage their unique strengths and capabilities, thereby overcoming the limitations of single-model approaches. The system is modular, allowing easy addition of new agents and communities, each sharing a common function but possessing distinct expertise. The project emphasizes a reward mechanism that evaluates and incentivizes agents based on their contributions to task completion, fostering a competitive yet cooperative environment akin to a Darwinian meritocracy within the AI community. This mechanism aims to optimize the recommendation and Mindstorm processes over time. The repository serves as a technical extension of the original NLSOM paper, providing functionalities for autonomous recommendation of relevant communities and agents, collaborative problem-solving through Mindstorm, and a reward system for agent performance. It features an elegant user interface supporting diverse file types and is designed for easy management and extensibility, currently hosting 16 communities and 34 agents. The project has been recognized with a Best Paper Award at NeurIPS 2023 and accepted for CVMJ 2025, highlighting its innovative approach to AI collaboration and intelligence. Installation is supported via Conda or Pip, with detailed setup instructions provided. Overall, NLSOM represents a significant advancement in multi-agent AI systems, promoting natural language communication and cooperative intelligence to tackle complex problems more effectively than isolated models.
https://github.com/metauto-ai/NLSOM
Also in Multi-Agent Frameworks
ruvnet/ruflo
Ruflo is a leading agent orchestration platform for Claude, enabling the deployment of intelligent multi-agent swarms, coordination of autonomous workflows, and building conversational AI systems.
Yeachan-Heo/oh-my-claude-sisyphus
Oh My Claude Sisyphus (OMC) is a multi-agent orchestration framework for Claude Code, simplifying complex AI agent workflows without a steep learning curve.
microsoft/JARVIS
JARVIS is a collaborative AI system that connects large language models with expert AI models from HuggingFace to autonomously plan, execute, and integrate complex AI tasks.
rowboatlabs/rowboat
Rowboat is an AI-powered platform that enables users to build and manage multi-agent swarms using natural language, integrating tools and knowledge for automated workflows and deployment via API or SDK.
cft0808/edict
Edict is an OpenClaw Multi-Agent Orchestration System featuring 9 specialized AI agents, a real-time dashboard, model configuration, and full audit trails, inspired by ancient Chinese imperial gove...
MemoriLabs/Memori
Memori is a versatile SQL native memory layer designed to enhance LLMs, AI agents, and multi-agent systems with advanced memory management, seamless integration, and high performance.
HKUDS/DeepCode
DeepCode is an open-source project that uses multi-agent AI systems to convert research papers and natural language into production-ready code through both CLI and web interfaces.