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
yohey-w/multi-agent-shogun
multi-agent-shogun is a Bash and tmux based orchestration system that runs many AI coding CLI instances at the same time under a hierarchy borrowed from feudal Japan. The user gives an order to the Shogun pane, the Shogun delegates to a Karo that breaks the work down, and seven Ashigaru workers plus one Gunshi strategist execute in parallel, each in its own visible tmux pane. Supported CLIs include Claude Code, OpenAI Codex, GitHub Copilot, Kimi Code, OpenCode, Cursor and Antigravity, so the system is not tied to a single vendor. Requirements are tmux, Bash 4 or newer and at least one supported CLI; setup runs a first_setup.sh script that configures dependencies and MCP, after which a launch script starts all agents. The main design claim is zero coordination overhead: agents communicate by reading and writing YAML files on disk rather than through model calls, so tokens are spent on actual work instead of orchestration. Every instruction, report and decision is therefore a plain text file that can be read, diffed and version-controlled, and progress is visible live in tmux panes and a dashboard. The chain of command is meant to prevent conflicts by giving each agent clear ownership and dedicated files with event-driven communication and no polling. Persistent preferences across sessions are handled through a Memory MCP server, and the project also advertises bottom-up automatic skill proposal. The README argues for driving flat-rate CLI subscriptions rather than per-token APIs, since running eight strong agents through an API would cost far more per hour than a monthly subscription. A note at the top records that the author has since moved to a single-agent successor project called kagemusha, while this project continues to work as is.
https://github.com/yohey-w/multi-agent-shogun
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.