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
Pan-Chera/Multi-Agent-CAD
MAC, short for Multi-Agent CAD, is a research framework from Tsinghua University IEI Lab for text-to-CAD generation. Instead of asking one large model to write an entire CAD program in a single long context, it decouples the job across four cooperating agents that hand structured intermediate results to each other, and it constrains how much test-time compute each stage may spend. The generated artefact is Python code for build123d, a parametric modelling library, so the output is an editable feature history that exports to STEP rather than a mesh, and the aider coding tool is used inside the loop to iterate on that code. The stated motivation is efficiency: the README compares MAC against a single-agent CAD skill baseline on the same ten benchmark prompts and reports 896 thousand tokens versus 103.9 million, roughly a thirteen-fold lower inference cost, and a feature pass rate of 99.3 percent against 97.9 percent. The benchmark parts exercise arrayed features, boolean operations, rotational patterns, helical sweeps and multi-body assemblies, and a separate gallery of ten original prompts covers ornaments and mechanisms such as a Geneva mechanism, an impeller and a multi-link chain. A harder scenario is print-in-place articulable models, where several independent solid bodies must coexist in one STEP file with clearances of roughly 0.4 to 1 millimetre so that the kinematic pairs move freely straight off the printer without assembly; examples include a ball-in-cage fidget toy and a gyroscope with pivot pins. A web UI drives a full pipeline run, and the documentation records per-prompt token and cost data. Installation uses a conda environment plus a pinned aider install, with a documented numpy conflict workaround. Python 3.11, MIT licensed.
https://github.com/Pan-Chera/Multi-Agent-CAD
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.