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
openai/openai-agents-python
The OpenAI Agents SDK is a lightweight yet powerful framework designed for building multi-agent workflows using large language models (LLMs). It provides a structured approach to creating agents that can be configured with specific instructions, tools, guardrails, and handoffs to enable complex interactions and task delegation among multiple agents. The SDK supports the orchestration of these agents in workflows that can be traced, debugged, and optimized through built-in tracing capabilities. Key concepts include Agents, which are LLMs configured with instructions and tools; Handoffs, which allow transferring control between agents; Guardrails, which provide safety checks for input and output validation; and Tracing, which tracks agent runs for monitoring and debugging purposes. The SDK is compatible with any model providers supporting the OpenAI Chat Completions API format, making it versatile for various LLM implementations. Users can easily get started by setting up a Python environment and installing the SDK via pip. The SDK includes examples demonstrating basic usage, handoffs between agents, and integration with function tools, showcasing its flexibility in handling different types of workflows. The agent loop mechanism ensures that agents interact in a controlled manner, processing tool calls and handoffs until a final output is produced. This final output can be structured or plain text, depending on the agent's configuration. The SDK also supports common agent patterns, allowing developers to model deterministic flows, iterative loops, and other complex behaviors. Tracing is a significant feature, providing automatic tracking of agent runs with extensible support for custom spans and integration with various external tracing platforms. This makes it easier to monitor, debug, and optimize multi-agent workflows. Overall, the OpenAI Agents SDK offers a comprehensive and flexible framework for developers looking to build sophisticated multi-agent systems leveraging LLMs, with a strong emphasis on safety, traceability, and extensibility.
https://github.com/openai/openai-agents-python
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.