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
aiming-lab/AutoResearchClaw
AutoResearchClaw is a pioneering project that aims to revolutionize scientific research by enabling fully autonomous and self-evolving paper generation. Users can simply provide an idea, and the system, leveraging advanced LLM agents and multi-agent debate, orchestrates the entire research process from hypothesis generation to experiment execution and paper drafting. Key features include multi-domain experiment agents (e.g., for high-energy physics, biology, statistics) that can autonomously select and utilize specialized tools and platforms. It also introduces ARC-Bench, a comprehensive benchmark with 55 open-ended autonomous research topics across various scientific fields for rigorous evaluation. The platform supports flexible skill loading, allowing for the integration of open-source and custom skills to enhance its research capabilities. A significant aspect of AutoResearchClaw is its Human-in-the-Loop (HITL) Co-Pilot System, which offers six intervention modes and per-stage policies for deep human-AI collaboration. This includes features like an Idea Workshop for hypothesis co-creation, a Baseline Navigator for experiment design review, and a Paper Co-Writer for collaborative drafting. The system also incorporates anti-hallucination claim verification, cost budget guardrails, and pipeline branching for parallel hypothesis exploration, ensuring robustness and reliability in the research process. AutoResearchClaw integrates with MetaClaw for cross-run learning, transforming pipeline failures into structured lessons and reusable skills, thereby improving its long-term performance and adaptability. It also boasts cross-platform support, running on various ACP-compatible agent backends and messaging platforms via OpenClaw bridge, making it highly accessible and versatile.
https://github.com/aiming-lab/AutoResearchClaw
Also in Multi-Agent Frameworks
paperclipai/paperclip
Open-source Node.js server and React dashboard that orchestrates teams of AI coding agents (Claude Code, Codex, Cursor, OpenCode and others) with org charts, budgets, goals and audit trails.
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.
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.
xbtlin/ai-berkshire
AI Berkshire is an investment research framework leveraging AI agents (Claude Code/Codex) to automate value investment analysis, synthesizing methodologies from renowned investors like Buffett and ...