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
ltjed/freephdlabor
freephdlabor is an open-source multiagent system for automating scientific research from hypothesis generation through experiments to a finished manuscript. A user launches it with a single task description, either a loose research direction or a detailed plan with objectives and target metrics, and a ManagerAgent orchestrates specialised workers such as an IdeationAgent that proposes research ideas, an ExperimentationAgent that runs computations and collects results, and a WriteupAgent that assembles the paper with figures and citations. The authors emphasise four design choices that separate it from earlier automated-science pipelines. Workflows are dynamic, so the system reorders and revises its plan in response to what experiments actually show instead of following a fixed sequence of stages. Agents are meant to be edited, added or removed by the user, with explicit customisation support so the same skeleton can be pointed at materials science, biology, economics or another field simply by supplying domain tools. Human feedback can be injected at any moment rather than only at predetermined checkpoints. Context management is built in so a run can sustain exploration over long horizons instead of being a single one-shot attempt. Installation uses a conda environment on Python 3.11 or later, with API keys for the chosen model providers set in a dotenv file and per-component model selection configurable in a YAML file; a CUDA-capable GPU is recommended for runs that involve real training. The repository includes an example generated paper, a demo video, a blog post explaining the intuition behind the architecture, and a technical report on arXiv. It is MIT licensed and aimed at researchers who want an always-running lab in their own field and at people studying how agent teams coordinate on open-ended work.
https://github.com/ltjed/freephdlabor
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.