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
cft0808/edict
Edict is an innovative Multi-Agent Orchestration System built on the OpenClaw framework, designed to manage complex AI workflows with a high degree of control and transparency. Inspired by the ancient Chinese 'Three Departments and Six Ministries' imperial system (三省六部制), it employs a hierarchical structure of 12 specialized AI agents (11 functional roles + 1 compatibility role). This system emphasizes a 'systemic auditing' mechanism, where the 'Menxia Province' agent rigorously reviews and potentially rejects plans, ensuring quality output before execution, a feature often lacking in other multi-agent frameworks like CrewAI or AutoGen. The project provides a comprehensive real-time dashboard, referred to as the 'Command Center' (军机处), offering 10 functional panels for monitoring and interaction. Key features include a Kanban board for task visualization, a department dispatch monitor, a 'Memorials' panel for audited task archives, and a 'Edict Library' for preset task templates. Users can also manage agent health, monitor token consumption, configure individual agent LLMs on the fly, and oversee installed skills. Edict addresses common pain points in multi-agent systems, such as lack of auditability, real-time monitoring, and intervention capabilities. It boasts features like task intervention (pause/cancel/resume), complete audit trails, hot-swappable LLM models per agent, and skill management. The system also includes an 'All Under Heaven News' feature for automated news collection and a 'Court Discussion' panel for multi-agent, multi-turn discussions, providing a robust and observable environment for AI agent collaboration.
https://github.com/cft0808/edict
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.
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.
xbtlin/ai-berkshire
AI Berkshire is an investment research framework leveraging AI agents (Claude Code/Codex) to automate value investment analysis, synthesizing methodologies from renowned investors like Buffett and ...