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
agentscope-ai/agentscope-java
AgentScope Java is a robust, agent-oriented programming framework designed to facilitate the creation of large language model (LLM)-powered applications in Java. It provides a comprehensive suite of features essential for developing intelligent agents, including the ReAct (Reasoning-Acting) paradigm for autonomous task execution and dynamic tool selection. The framework emphasizes control and reliability in production environments through mechanisms such as safe interruption, graceful cancellation, and Human-in-the-Loop intervention via a Hook system. Key highlights include built-in tools like PlanNotebook for structured task management, Structured Output for guaranteed type-safe responses with automated error correction, and Long-term Memory with semantic search capabilities for persistent storage. It also integrates RAG (Retrieval-Augmented Generation) for knowledge base grounding. AgentScope Java is engineered for seamless integration with existing enterprise infrastructure, supporting MCP (Multi-Agent Communication Protocol) for extending agent capabilities and A2A (Agent-to-Agent) protocol for distributed multi-agent collaboration via service discovery. The framework is production-grade, featuring a reactive architecture for high performance, GraalVM native image compilation for fast cold starts, and a Security Sandbox for isolated execution of untrusted code. Observability is provided through native OpenTelemetry integration and AgentScope Studio for debugging and monitoring. It aims to empower developers to build sophisticated, reliable, and scalable AI agent applications in Java.
https://github.com/agentscope-ai/agentscope-java
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.