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
cognizant-ai-lab/neuro-san-studio
Neuro SAN Studio is the example and tutorial companion to Neuro SAN (Neuro AI System of Agent Networks), the open-source multi-agent orchestration framework from Cognizant AI Lab that powers the Cognizant Neuro AI Multi-Agent Accelerator. The studio packages ready-to-run examples, tutorials and tooling so that a researcher, a developer or a domain expert can design, test and deploy agent networks without first building the orchestration layer. In Neuro SAN an entire agent network is declared in HOCON configuration files rather than written in code, which is what allows non-programmers to lay out agent interactions. At run time several LLM-backed agents collaborate on a task and delegate subtasks to one another through the AAOSA protocol, an adaptive communication scheme in which agents decide themselves how work is handed off, keeping decision-making decentralised instead of depending on one model that holds all the expertise and context. Sly-Data is the mechanism for passing sensitive values between agents without exposing them to the language models. The framework includes an Agent Network Designer, a meta-agent shipped as an example that takes a high-level description of a use case and generates a custom agent network for it. Tool integration is pluggable: custom Python coded tools, APIs and databases, plus external ecosystems including Agentforce, Agentspace, CrewAI, MCP servers, A2A agents and LangChain tools. Detailed logging, tracing and session-level metrics are built in for transparency, debugging and operational monitoring, and the nsflow interface provides a web front end for exercising networks. The repository is distributed on PyPI as neuro-san-studio alongside the neuro-san library itself, and the README links video walkthroughs covering the designer, a framework overview and a quick start. It suits teams evaluating declarative multi-agent orchestration or prototyping vertical agent applications before committing to a production stack.
https://github.com/cognizant-ai-lab/neuro-san-studio
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.