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
PurpleAILAB/Decepticon
Decepticon is an advanced autonomous Red Team agent designed to simulate realistic attack chains, including reconnaissance, exploitation, privilege escalation, lateral movement, and C2 operations, mimicking the tactics of a human adversary. Unlike typical AI hacking demos, it emphasizes a disciplined approach by first generating a complete engagement package, including Rules of Engagement (RoE), Concept of Operations (ConOps), Deconfliction Plan, and OPPLAN with MITRE ATT&CK mapping, ensuring all actions adhere to defined rules. The platform supports interactive shells within persistent tmux sessions, allowing agents to send follow-up commands to interactive tools like msfconsole. Decepticon operates with hardened sandbox isolation, running all commands within a Kali Linux sandbox on a dedicated operational network, separate from the management plane. Its architecture features a two-network design for management services and sandbox/target environments, integrating Neo4j for knowledge graph persistence. The system comprises 16 specialist agents, organized by kill chain phases (Orchestration, Reconnaissance, Exploitation, Post-Exploitation, etc.), each with a fresh context window per objective to eliminate noise. It utilizes a tier-based, credentials-aware fallback chain for LLM providers (Anthropic, OpenAI, Google Gemini, etc.) and offers an SDK for library usage. Decepticon also includes benchmarks against various security challenges and aims to develop an "Offensive Vaccine" loop to turn findings into defensive improvements.
https://github.com/PurpleAILAB/Decepticon
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.