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
Ido-Levi/Hephaestus
Hephaestus is a semi-structured agentic framework in Python for coordinating multiple AI agents on complex software work. Instead of a fixed graph where every branch needs instructions written in advance, it defines logical phase types and lets agents create new tasks in any phase based on what they find. The default setup uses three phases: analysis for understanding, planning and investigation, implementation for building, fixing and optimizing, and validation for testing and quality checks. Any agent can open a ticket in any phase, so a validation agent that notices a caching pattern can spawn an analysis task to investigate it while continuing its own work, and a failing test can spawn an implementation task followed by a retest. Work is coordinated through Kanban tickets with blocking relationships, producing a branching task tree that reflects real discoveries rather than anticipated scenarios. Agents run in parallel, and a Guardian component monitors agent trajectories and reports a coherence measure, with a real-time view of active agents across phases. The documentation describes a worked example that starts from a product requirements document: one analysis agent identifies components, spawns parallel implementation tasks for authentication, REST API, frontend, database schema and background workers, and later phases branch further into optimization and bug fix work. The project also ships Hephaestus Dev, a preconfigured setup with five ready workflows for software development: building software from a PRD, systematic bug fixing, indexing a repository into memory, adding features to an existing codebase following its patterns, and generating documentation. It is launched by pointing a runner script at a project path. The project requires Python 3.8 or newer, is licensed under AGPL-3.0 and is marked alpha, with hosted documentation and example workflows.
https://github.com/Ido-Levi/Hephaestus
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.