OSU-NLP-Group/Explorer
[ACL'25 (Findings)] Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
This project helps AI developers and researchers train and evaluate multimodal web agents capable of navigating websites and performing tasks. It takes raw web interaction data (trajectories) as input, processes it, and outputs trained models that can synthesize new web navigation paths. The primary users are researchers and engineers working on advanced AI for web automation.
Use this if you are developing or evaluating AI agents that need to interact with websites, especially for complex or exploratory tasks where agents learn to navigate based on visual and textual information.
Not ideal if you are looking for an off-the-shelf solution for simple web scraping or basic browser automation without deep AI agent training.
Stars
27
Forks
1
Language
Python
License
MIT
Category
Last pushed
Feb 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/OSU-NLP-Group/Explorer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DataBassGit/AgentForge
Extensible AGI Framework
agentjido/jido
🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic...
genielabs/HomeGenie
HomeGenie: The Programmable Intelligence with 100% Local Agentic AI.
vishalmysore/Tools4AI
Agentic Framework for Java, written in 100% Java using Gemini, OpenAI, LocalAI, Anthropic....
existence-master/Sentient
A personal AI assistant for everyone