Shubhamsaboo/awesome-llm-apps
A curated collection of impressive LLM-powered AI applications featuring RAG, AI Agents, Multi-agent Teams, and open-source models from leading AI providers like OpenAI, Anthropic, and Google Gemini.
Awesome AI Agents › AI Agent Ecosystems
crewAIInc/crewAI
CrewAI is a high-performance, flexible Python framework designed for orchestrating role-playing, autonomous AI agents that collaborate to solve complex tasks. Built entirely from scratch and independent of other agent frameworks like LangChain, CrewAI offers developers both high-level simplicity and granular low-level control, making it suitable for a wide range of applications from simple automations to enterprise-grade AI workflows. The framework introduces two core concepts: Crews and Flows. Crews are teams of AI agents with autonomous decision-making capabilities, role-based collaboration, and dynamic task delegation, enabling natural and flexible problem-solving. Flows provide event-driven, production-ready workflows that allow precise control over task orchestration, state management, and integration with Python code, supporting complex business logic with conditional branching. The synergy between Crews and Flows empowers developers to build sophisticated, maintainable AI applications that balance autonomy with control. CrewAI is optimized for speed and minimal resource usage, making it a lean and lightning-fast solution. It supports extensive customization at all levels, from overall system architecture to individual agent behaviors and execution logic. The framework is backed by a robust community of over 100,000 certified developers, offering comprehensive support and learning resources, including courses on multi-agent systems and advanced use cases. For enterprises, CrewAI offers the Enterprise Suite, a comprehensive package that includes the Crew Control Plane—a centralized platform for managing, monitoring, and scaling AI agents and workflows. Key features of the Enterprise Suite include real-time tracing and observability, seamless integration with existing enterprise systems, advanced security and compliance measures, actionable analytics, and 24/7 dedicated support. Deployment options include both on-premise and cloud environments, catering to diverse organizational needs. CrewAI's design philosophy emphasizes bridging the gap between simplicity, flexibility, and performance, making it an ideal choice for developers and organizations aiming to implement intelligent, autonomous multi-agent automation solutions. The framework also provides detailed documentation, community forums, and interactive chat support to facilitate adoption and development.
https://github.com/crewAIInc/crewAI
Also in AI Agent Ecosystems
lobehub/lobehub
LobeHub is a platform that enables users to find, build, and collaborate with AI agent teammates that evolve with them, facilitating multi-agent collaboration and transforming productivity through AI-driven workspaces.
FoundationAgents/MetaGPT
MetaGPT is a multi-agent AI framework that simulates a software company by assigning GPT-based roles to collaboratively automate software development from natural language requirements.
ComposioHQ/awesome-claude-skills
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows.
shanraisshan/claude-code-best-practice
This repository provides best practices and implementations for leveraging Claude AI's agentic engineering features, including subagents, commands, skills, workflows, and memory.
HKUDS/nanobot
nanobot is an open-source, lightweight personal AI agent, providing a WebUI, chat channels, tools, memory, and model routing for long-running workflows and automation.
sickn33/agentic-awesome-skills
Agentic Awesome Skills is an installable GitHub library providing over 1,900 agentic skills for various AI coding assistants like Claude Code, Cursor, and Gemini CLI.
mindsdb/mindshub
MindsHub Cowork is a unified workspace for delegating projects to AI, connecting data, routing work to various models, and publishing agent outputs as web applications.