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
lgy0404/LearnAct
LearnAct is an advanced framework designed to enhance mobile GUI agents through few-shot learning using human demonstrations. The project introduces LearnGUI, a comprehensive benchmark dataset specifically created for studying demonstration-based learning in mobile GUI agents. LearnGUI includes 2,252 offline tasks and 101 online tasks across 73 diverse mobile applications, featuring high-quality human demonstrations with an average of 13.2 steps per task. It supports few-shot learning with k-shot combinations and provides multi-dimensional similarity metrics across instruction, UI, and action dimensions. LearnAct framework integrates three specialized agents: DemoParser, which extracts usable knowledge from demonstration trajectories; KnowSeeker, which retrieves relevant demonstration knowledge for current tasks; and ActExecutor, which executes tasks by combining instructions, GUI environment, and demonstration knowledge. The project addresses the challenge of generalization in mobile GUI agents by focusing on improving performance in unseen scenarios through demonstration-based learning rather than relying on massive datasets for universal generalization. The repository includes the LearnGUI benchmark dataset available on HuggingFace, inference and evaluation code for LearnAct on LearnGUI-Offline, and plans for future releases including LearnAct on LearnGUI-Online and real-world deployment demos. LearnAct stands out by providing a unified demonstration benchmark and a multi-agent framework that leverages human demonstrations to improve task completion in mobile GUI automation. This approach offers a novel direction for research and development in mobile GUI agents, emphasizing adaptability and efficiency in diverse real-world applications.
https://github.com/lgy0404/LearnAct
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 ...