AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
☆606Jul 17, 2026Updated this week
Alternatives and similar repositories for AgentLab
Users that are interested in AgentLab are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 🌎💪 BrowserGym, a Gym environment for web task automation☆1,284Updated this week
- WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?☆258Apr 25, 2026Updated 2 months ago
- TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle☆318Dec 16, 2025Updated 7 months ago
- Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"☆1,550Nov 26, 2025Updated 7 months ago
- A verified version of the WebArena Benchmark☆44Mar 8, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- VisualWebArena is a benchmark for multimodal agents.☆482Nov 9, 2024Updated last year
- Standardize benchmark wrapping so the community can wrap various otherwise-incompatible benchmarks uniformly and use them everywhere.☆52Updated this week
- An Illusion of Progress? Assessing the Current State of Web Agents☆191Jun 25, 2026Updated 3 weeks ago
- DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats☆62Sep 12, 2025Updated 10 months ago
- Drive OSS standards and tools for data curation and evaluation creation for state of the art AI agents☆54Updated this week
- An agent benchmark with tasks in a simulated software company.☆747Nov 17, 2025Updated 8 months ago
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆535Jun 6, 2025Updated last year
- [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments☆3,026Updated this week
- [ACL'25 (Findings)] Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents☆29Feb 17, 2026Updated 5 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆427Updated this week
- AWM: Agent Workflow Memory☆447Dec 22, 2025Updated 6 months ago
- Setup scripts for the WebArena benchmark☆22Jun 19, 2025Updated last year
- [NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web" -- the first LLM-based web agent and benchmark for generalist w…☆1,015Nov 5, 2025Updated 8 months ago
- Awesome GUI Agent Paper List☆861Jun 28, 2026Updated 3 weeks ago
- COLM2026☆36Jul 9, 2026Updated last week
- Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research☆327Updated this week
- AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents☆59Jan 28, 2025Updated last year
- Towards Large Multimodal Models as Visual Foundation Agents☆270Apr 24, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- SafeArena is a benchmark for assessing the harmful capabilities of web agents☆24Apr 23, 2025Updated last year
- WebLINX is a benchmark for building web navigation agents with conversational capabilities☆162Feb 11, 2025Updated last year
- [ICLR2025 Spotlight] Agent Trajectory Synthesis via Guiding Replay with Web Tutorials☆60Feb 21, 2025Updated last year
- [NeurIPS'25 D&B] Mind2Web-2 Benchmark: Evaluating Agentic Search with Agent-as-a-Judge☆111May 17, 2026Updated 2 months ago
- AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories☆47Aug 7, 2025Updated 11 months ago
- Helping AI practitioners better understand their datasets and models in text classification. From ServiceNow.☆72Dec 23, 2024Updated last year
- ☆29Jun 5, 2025Updated last year
- [NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis☆172Jun 18, 2026Updated last month
- SkillWeaver is a framework to enable web agent self-improvement through environment exploration and skill synthesis.☆143Apr 14, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Agent Skill Induction: "Inducing Programmatic Skills for Agentic Tasks"☆42Apr 24, 2025Updated last year
- ☆17May 6, 2025Updated last year
- GUI Grounding for Professional High-Resolution Computer Use☆383Jun 17, 2026Updated last month
- Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"☆1,110Mar 4, 2024Updated 2 years ago
- A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)☆3,586Feb 8, 2026Updated 5 months ago
- [ACL 2025] Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis☆188Oct 8, 2025Updated 9 months ago
- Code and Data for Tau-Bench☆1,337Mar 18, 2026Updated 4 months ago