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
matiasmolinas/evolving-agents
The Evolving Agents Toolkit (EAT) is a comprehensive Python toolkit designed to build advanced, autonomous multi-agent ecosystems that can dynamically adapt, learn, and evolve to achieve complex goals. It is tailored for AI-First strategies where agent-driven workflows mimic sophisticated human processes by orchestrating discovery, creation, execution, and evolution of agents and tools. The core of EAT is the SystemAgent, a central orchestrator that receives high-level goals from users or external systems and manages the entire lifecycle of agents and tools to fulfill these goals. The toolkit features a SmartLibrary, a semantic repository with dual embedding strategies for task-aware component retrieval, enabling agents to find relevant tools and components based on their applicability to specific tasks rather than just their content. Communication and coordination among agents are facilitated by the SmartAgentBus, which supports dynamic discovery, routing, and interaction through separate system and data buses, promoting a microservices-like architecture. EAT supports adaptive evolution of its components, allowing agents and tools to improve over time based on feedback and changing requirements. The modular design allows integration with various agent and tool providers such as BeeAI and OpenAI, governed by a Firmware module that enforces operational rules and safety guardrails. Additionally, the toolkit incorporates SmartContext to provide task-specific context, enhancing agent performance by reducing irrelevant information. Optional components like ArchitectZero enable collaborative design and self-improvement of the ecosystem. Overall, EAT empowers developers to create complex, goal-oriented AI systems that autonomously manage and evolve their capabilities, making it ideal for applications requiring robust orchestration, adaptability, and intelligent component management.
https://github.com/matiasmolinas/evolving-agents
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.
crewAIInc/crewAI
CrewAI is a fast, flexible Python framework for orchestrating autonomous, role-playing AI agents that collaborate to solve complex tasks, offering both high-level simplicity and low-level control for enterprise-grade AI automation.
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.