AgentLab and HelloAgents

AgentLab provides a comprehensive benchmarking and testing infrastructure for web agents, while HelloAgents offers a lightweight tutorial-based framework for agent development, making them complements that could be used together where HelloAgents serves as a starting point and AgentLab validates the resulting agents.

AgentLab
72
Verified
HelloAgents
67
Established
Maintenance 13/25
Adoption 10/25
Maturity 25/25
Community 24/25
Maintenance 17/25
Adoption 10/25
Maturity 15/25
Community 25/25
Stars: 530
Forks: 108
Downloads:
Commits (30d): 1
Language: Python
License:
Stars: 793
Forks: 215
Downloads:
Commits (30d): 6
Language: Python
License:
No risk flags
No Package No Dependents

About AgentLab

ServiceNow/AgentLab

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

This is a framework for researchers and developers working on AI agents that can interact with websites. It helps you build, test, and compare how well these 'web agents' perform on various online tasks. You feed in your experimental web agents and get back performance benchmarks, helping you understand their strengths and weaknesses across different web environments.

AI Agent Development Web Automation Agent Benchmarking AI Research Large Language Models

About HelloAgents

jjyaoao/HelloAgents

A agent framework based on the tutorial hello-agents

This project helps developers build sophisticated AI applications that involve multiple large language models working together. It provides a robust framework for managing how these AI agents interact, share information, and use external tools. Developers use this to integrate various LLMs, manage conversation history, track task progress, and implement complex decision-making processes, resulting in more reliable and intelligent AI systems.

AI-development LLM-orchestration multi-agent-systems AI-engineering AI-application-development

Scores updated daily from GitHub, PyPI, and npm data. How scores work