ServiceNow / AgentLab
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
☆258Updated last week
Alternatives and similar repositories for AgentLab:
Users that are interested in AgentLab are comparing it to the libraries listed below
- WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?☆167Updated 3 weeks ago
- TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle☆230Updated this week
- Code for the paper 🌳 Tree Search for Language Model Agents☆184Updated 7 months ago
- 🌎💪 BrowserGym, a Gym environment for web task automation☆597Updated last week
- AWM: Agent Workflow Memory☆254Updated last month
- VisualWebArena is a benchmark for multimodal agents.☆315Updated 4 months ago
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym☆391Updated this week
- An agent benchmark with tasks in a simulated software company.☆258Updated this week
- This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects.☆264Updated this week
- [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents☆185Updated last week
- 🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Pap…☆155Updated 3 months ago
- Building a comprehensive and handy list of papers for GUI agents☆243Updated 3 weeks ago
- Code and Data for Tau-Bench☆325Updated last month
- OS-ATLAS: A Foundation Action Model For Generalist GUI Agents☆293Updated 3 weeks ago
- ☆374Updated last month
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆320Updated last month
- Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction☆254Updated this week
- WebLINX is a benchmark for building web navigation agents with conversational capabilities☆144Updated last month
- Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"☆462Updated 11 months ago
- ☆180Updated 2 weeks ago
- Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.☆617Updated this week
- [NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents☆309Updated 6 months ago
- Official repo for paper DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.☆323Updated 2 weeks ago
- AndroidWorld is an environment and benchmark for autonomous agents☆231Updated last week
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆163Updated this week
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆422Updated 5 months ago
- ☆159Updated 7 months ago