ππͺ BrowserGym, a Gym environment for web task automation
β1,136Feb 10, 2026Updated 2 weeks ago
Alternatives and similar repositories for BrowserGym
Users that are interested in BrowserGym are comparing it to the libraries listed below
Sorting:
- AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reβ¦β522Feb 10, 2026Updated 2 weeks ago
- WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?β234Feb 17, 2026Updated last week
- Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"β1,337Nov 26, 2025Updated 3 months ago
- VisualWebArena is a benchmark for multimodal agents.β436Nov 9, 2024Updated last year
- TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycleβ302Dec 16, 2025Updated 2 months ago
- WebLINX is a benchmark for building web navigation agents with conversational capabilitiesβ160Feb 11, 2025Updated last year
- [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentsβ2,587Feb 20, 2026Updated last week
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RLβ510Jun 6, 2025Updated 8 months ago
- AWM: Agent Workflow Memoryβ397Dec 22, 2025Updated 2 months ago
- [NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web" -- the first LLM-based web agent and benchmark for generalist wβ¦β947Nov 5, 2025Updated 3 months ago
- An agent benchmark with tasks in a simulated software company.β643Nov 17, 2025Updated 3 months ago
- OS-ATLAS: A Foundation Action Model For Generalist GUI Agentsβ435Apr 20, 2025Updated 10 months ago
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]β632Jul 29, 2025Updated 6 months ago
- β18Jan 3, 2025Updated last year
- [ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multβ¦β824Feb 3, 2025Updated last year
- Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"β1,028Mar 4, 2024Updated last year
- An Illusion of Progress? Assessing the Current State of Web Agentsβ146Jan 2, 2026Updated last month
- Building a comprehensive and handy list of papers for GUI agentsβ636Oct 27, 2025Updated 4 months ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.β368Feb 19, 2026Updated last week
- Code for the paper π³ Tree Search for Language Model Agentsβ220Jul 25, 2024Updated last year
- β67Mar 6, 2025Updated 11 months ago
- Agentlessπ±: an agentless approach to automatically solve software development problemsβ2,010Dec 22, 2024Updated last year
- β41Jul 21, 2024Updated last year
- Towards Large Multimodal Models as Visual Foundation Agentsβ256Apr 24, 2025Updated 10 months ago
- Windows Agent Arena (WAA) πͺ is a scalable OS platform for testing and benchmarking of multi-modal AI agents.β824Feb 11, 2026Updated 2 weeks ago
- [ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interactionβ379Mar 7, 2025Updated 11 months ago
- π₯ Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web witβ¦β6,457Updated this week
- [COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wildβ4,710Nov 18, 2024Updated last year
- A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)β3,166Feb 8, 2026Updated 2 weeks ago
- Multimodal computer agent data collection programβ162Dec 5, 2025Updated 2 months ago
- π» A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.β1,115Aug 17, 2025Updated 6 months ago
- Agent driven automation starting with the web. Try it: https://www.emergence.ai/web-automation-apiβ1,219Jun 3, 2025Updated 8 months ago
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"β70Dec 9, 2024Updated last year
- Interaction-first method for generating demonstrations for web-agents on any websiteβ51Apr 29, 2025Updated 9 months ago
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]β148Nov 26, 2024Updated last year
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.β2,512Feb 18, 2026Updated last week
- Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.β440Feb 16, 2026Updated last week
- MiniWoB++: a web interaction benchmark for reinforcement learningβ371May 5, 2025Updated 9 months ago
- An LLM-based Web Navigating Agent (KDD'24)β926Sep 27, 2024Updated last year