This project includes code for using the AsyncWebRL and WebGym frameworks to train web agent models.
☆50Jun 9, 2026Updated 4 months ago
Alternatives and similar repositories for webgym
Users that are interested in webgym are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for NeurIPS 2026 paper OpenWebRL: Online Multi-Turn Reinforcement Learning for Visual Web Agents☆56Aug 17, 2026Updated 2 months ago
- ☆70Mar 6, 2025Updated last year
- Official code for NeurIPS 2026 paper "GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially…☆74Mar 29, 2026Updated 7 months ago
- ☆20Sep 16, 2025Updated last year
- Throughput-oriented multi-turn inference engine for KernelBench [ICML '25]☆25May 27, 2025Updated last year
- 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.
- Scale digital agent rollouts without pain.☆39Jun 18, 2026Updated 4 months ago
- ☆76Jun 10, 2025Updated last year
- A LLM-based AI agent for Pokemon Red Battles☆11Jul 1, 2025Updated last year
- A simple and easy to use implementation of the soft actor-critic algorithm.☆15Sep 2, 2022Updated 4 years ago
- CUA-Gym-Hub: mock web apps as reproducible RL training environments for computer-use agents☆82Sep 3, 2026Updated last month
- ☆18Feb 28, 2026Updated 8 months ago
- DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents☆13Oct 9, 2026Updated 3 weeks ago
- ☆23Jun 10, 2025Updated last year
- Official code for the paper "SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction"☆22Sep 9, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [ICML 2026] ScreenParse☆21Jul 20, 2026Updated 3 months ago
- SimKO: Simple Pass@K Policy Optimization☆31Oct 24, 2025Updated last year
- Code for Diagnosing Bottlenecks in Deep Q-learning. Contains implementations of tabular environments plus solvers.☆17May 14, 2019Updated 7 years ago
- EvoCUA: Evolving Computer Use Agent☆355Mar 31, 2026Updated 6 months ago
- [CVPR 2026] ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering☆20Mar 4, 2026Updated 7 months ago
- An Illusion of Progress? Assessing the Current State of Web Agents☆209Updated this week
- [ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction☆394Mar 7, 2025Updated last year
- [NeurIPS 2025 Spotlight] Official repository for "Web-Shepherd: Advancing PRMs for Reinforcing Web Agents"☆61May 21, 2025Updated last year
- Build and train systems of agents.☆33Updated this week
- 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.
- [JMLR] Gradual Domain Adaptation: Theory and Algorithms☆11Jan 14, 2025Updated last year
- Code implementation for "TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems"☆17May 12, 2026Updated 5 months ago
- Navi-Bench: benchmarking web agents on everyday tasks directly on real websites☆22Oct 2, 2026Updated 3 weeks ago
- ☆28Jul 10, 2026Updated 3 months ago
- The code and datasets of our ACM MM 2024 paper "Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed …☆11Sep 27, 2024Updated 2 years ago
- [NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis☆184Jun 18, 2026Updated 4 months ago
- Gym-Anything: Turn any Software into an Agent Environment☆297Updated this week
- Train a tiny LLaMA model from scratch to repeat your words using Reinforcement Learning from Human Feedback (RLHF)☆18May 23, 2024Updated 2 years ago
- The model, data and code for OpenMobile☆52Jul 9, 2026Updated 3 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.
- ☆24Feb 16, 2022Updated 4 years ago
- Scalable pipeline for synthesizing verifiable RLVR training data for computer-use agents☆224Aug 13, 2026Updated 2 months ago
- SkillGrad: Optimizing Agent Skills Like Gradient Descent☆28May 28, 2026Updated 5 months ago
- An unofficial LaTeX Beamer theme for Shanghai Innovation Institute (SII).☆20Jun 8, 2026Updated 4 months ago
- ☆16Sep 24, 2026Updated last month
- ☆32Sep 4, 2025Updated last year
- ☆56Nov 26, 2024Updated last year