ranpox / awesome-computer-use
This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects.
☆241Updated this week
Alternatives and similar repositories for awesome-computer-use:
Users that are interested in awesome-computer-use are comparing it to the libraries listed below
- OS-ATLAS: A Foundation Action Model For Generalist GUI Agents☆287Updated last week
- Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction☆245Updated last month
- [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents☆176Updated this week
- Building a comprehensive and handy list of papers for GUI agents☆227Updated last week
- AWM: Agent Workflow Memory☆245Updated last month
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆315Updated 3 weeks ago
- 💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.☆511Updated this week
- VisualWebArena is a benchmark for multimodal agents.☆306Updated 3 months ago
- 🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/☆215Updated 3 months ago
- The model, data and code for the visual GUI Agent SeeClick☆323Updated 3 months ago
- AndroidWorld is an environment and benchmark for autonomous agents☆218Updated last week
- Code for the paper 🌳 Tree Search for Language Model Agents☆184Updated 7 months ago
- Official repo for paper DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.☆313Updated last week
- Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis☆108Updated last month
- WebLINX is a benchmark for building web navigation agents with conversational capabilities☆143Updated 2 weeks ago
- AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and re…☆244Updated this week
- An agent benchmark with tasks in a simulated software company.☆251Updated this week
- [ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large mult…☆718Updated last month
- [ICLR 2025] A trinity of environments, tools, and benchmarks for general virtual agents☆195Updated last week
- Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.☆604Updated 3 months ago
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and …☆336Updated 8 months ago
- ☆366Updated last month
- Official implementation for "You Only Look at Screens: Multimodal Chain-of-Action Agents" (Findings of ACL 2024)☆220Updated 7 months ago
- Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi e…☆400Updated 2 months ago
- Code and Data for Tau-Bench☆313Updated last month
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym☆369Updated this week
- A compilation of the best multi-agent papers☆398Updated this week
- Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhan…☆620Updated 9 months ago