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
swarmclawai/swarmclaw
SwarmClaw is an open-source, self-hosted runtime and framework for running teams of autonomous AI agents. It is written in TypeScript, distributed on npm, and positioned as an alternative to running agents directly through a single coding CLI or building orchestration by hand on top of a library. The runtime executes agents continuously rather than only on demand: agents have heartbeats, can be put on schedules, and can delegate work to other agents, which makes long-running swarms and orchestrator patterns possible. Each agent has durable memory and persistent conversation history, so state survives restarts and sessions. Tooling comes from the Model Context Protocol, and agents can also acquire runtime skills, including a reviewed conversation-to-skill learning path where behaviour demonstrated in a conversation can be promoted into a reusable skill after review. Model access is broad, spanning more than twenty-three providers including Anthropic Claude, OpenAI, Google Gemini, OpenRouter, local Ollama, DeepSeek and Groq, and it can also drive existing agent CLIs such as Claude Code, Codex, Gemini CLI, OpenCode, Copilot CLI, Factory Droid, Cursor Agent, Qwen Code and Goose, as well as OpenClaw and Hermes gateways. The web interface acts as an agent dashboard: an org chart view visualises agent teams, delegation edges and live activity, while a chat view gives each agent a conversation with its history, its tools and operator controls for intervening. Because the whole stack is self-hosted, conversations, memory and credentials stay on the operator's own infrastructure. The project ships continuous integration, tagged releases, documentation and an extension tutorial for adding custom capabilities. It suits users who want a persistent home base for multi-agent workflows rather than one-off agent invocations.
https://github.com/swarmclawai/swarmclaw
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.