#multi-agent-orchestration

OpenHarness, developed by HKUDS, is an open-source, lightweight Python framework providing essential infrastructure for advanced AI Agents. Functioning as a comprehensive 'Agent Harness,' it equips large language models with robust tool-use capabilities (43+ tools), skill management, persistent memory, and sophisticated multi-agent coordination. Key features include parallel streaming agent loops, intelligent context compression, multi-level permission governance, and a flexible plugin ecosystem. OpenHarness empowers researchers and developers to deeply understand, experiment with, and extend production-grade AI Agents. Its capabilities are showcased by ohmo, an intelligent assistant for multi-day tasks like code generation and PR management across platforms such as Feishu and Slack, leveraging existing LLM subscriptions without extra API keys.

Claude-Code-Game-Studios by Donchitos is an innovative AI Agent product that transforms Claude Code's capabilities into a highly organized virtual game development studio. It integrates 49 specialized AI agents and 72 refined workflow skills, automating and optimizing every stage of game development from concept generation to testing and deployment. A unique coordination system precisely simulates real studio hierarchies and collaboration, ensuring seamless AI agent synergy and efficient project management. This platform offers developers a comprehensive AI-driven solution to significantly enhance development efficiency, shorten cycles, and empower creators to focus purely on innovation.

BMAD-METHOD is an open-source, AI-driven agile development framework designed for end-to-end software engineering. It features scale-domain-adaptive intelligence that adjusts planning depth based on project complexity, from bug fixes to enterprise systems. Utilizing 12+ specialized domain agents and 34+ structured workflows, it facilitates professional collaboration between users and AI. The system integrates seamlessly with AI IDEs like Claude Code and Cursor, offering a 'Party Mode' for multi-agent discussions and a comprehensive module ecosystem for game dev, testing, and creative intelligence.

Agent Council is a consensus-gathering skill for AI CLIs like Claude Code and Codex CLI. Inspired by Karpathy's LLM Council, it orchestrates multiple locally installed AI agents to provide independent perspectives, which are then synthesized by a 'Chairman' agent. By utilizing existing CLI subscriptions instead of direct API calls, it avoids additional costs. It supports a structured 3-stage workflow—gathering, collection, and synthesis—with parallel execution for high efficiency.