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
KunAgent/Kun
Kun is an AI agent workspace with a 'local-first' philosophy, catering to individuals and teams who need to translate ideas into verifiable results across various domains. It integrates coding, writing, design, research, and automation within a single product. A core feature is its shared runtime, allowing desktop GUI, terminal TUI, backend tasks, and mobile connections to share threads, plans, reviews, model connections, and task records, ensuring consistency and traceability. Unlike traditional chatbots, Kun focuses on continuous workflows from requirements to final delivery, incorporating context, planning, file modifications, testing, review, and deployment. The platform supports diverse use cases: for developers, it offers AI coding and code review; for writers, AI writing and document export; for designers, AI design and prototyping; for researchers, multi-modal research with PDFs and images; and for automation, multi-agent automation. Users can interact via a desktop GUI for visual oversight or a TUI for keyboard-centric operations, both leveraging the same underlying Kun runtime. It's model-agnostic, supporting various AI models through subscriptions, API keys, and custom providers. User data (conversations, preferences, logs) is stored locally by default, ensuring data privacy, though cloud models may process prompts and context. Kun also introduces an experimental Agent Graph for complex, multi-stage tasks, allowing a Lead Agent to create dependency graphs, dispatch sub-agents, monitor progress, and validate outcomes. This ensures that sub-agents operate within defined permissions and that all stages are verified before proceeding, providing a robust framework for managing intricate AI-driven projects.
https://github.com/KunAgent/Kun
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.