A curated catalog of 500+ AI agent projects organized by major frameworks and industries, providing links to open-source examples, tutorials, and working code. Developers can clone the repository and run self-contained Python agents locally, though individual agent execution requires user-provided API keys for external models.
Project overview
It aggregates 500-plus runnable examples and framework comparisons across LangGraph, CrewAI, AutoGen, and Agno into a single repository, lowering discovery time for developers and researchers seeking practical AI agent implementations.
Project type
AI Agent
Deployment
Refer to project documentation
License
MIT
Best for
Developers and researchers seeking a structured catalog of 500+ open-source AI agent examples across LangGraph, CrewAI, AutoGen, and Agno.
Enterprise teams evaluating AI frameworks using comparison tables for multi-agent support, streaming, and local LLM capabilities.
Key capabilities
A curated catalog of 500+ AI agent projects organized by major frameworks (LangGraph, CrewAI, AutoGen, Agno) and industries (Healthcare, Finance, Education, Cybersecurity, etc.) providing links to open-source projects.
Provides self-contained agent code examples with their own requirements.txt and .env.example, runnable from the agents/ directory without monorepo setup.
Provides a comparison table of major AI frameworks detailing use cases, complexity, multi-agent support, streaming, and local LLM capabilities.
Includes a dedicated directory for learning via courses, such as crewai_mcp_course/.
Limitations and risks
Python knowledge and coding are required to install dependencies, configure environment variables, and run the agents via CLI.
Minimum hardware, OS requirements, and GPU dependencies are not documented.
Telemetry collection and end-to-end local data boundaries are not documented; agents require external API keys for model interaction.
Getting started
Clone the repository using git clone, navigate to the 500-AI-Agents-Projects directory, and enter a specific agent folder such as agents/01-web-research-agent.
Install the required Python packages using pip install -r requirements.txt, copy the .env.example file to .env, provide the necessary API keys, and execute the agent using python agent.py via CLI.
Alternatives and comparisons
An intelligent pairing LLM agent that autonomously builds ML/AI baselines and participates in Kaggle competitions, in contrast to a static project catalog.
A local AI workbench built around a Code Agent designed for long-horizon engineering tasks and document generation, rather than example discovery.
Composable engineering skills for AI coding agents that enforce test-driven development and code review, instead of runnable examples.