xlyu0106/CUA-Master
Agent
Can I trust it?
Be careful with this one.
Warnings Check
Very new: it was created 5 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.
Quick checks from public data. They help, but they are no guarantee.
What it is
A research codebase for scaling computer-use agents. It harvests instructional videos, scores their suitability, reconstructs seed task trajectories, synthesizes new verifiable tasks, and collects agent trajectories in sandboxed VMs with snapshot-rollback retries, then prepares…
Who it's for
ML researchers building computer-use agents who need pipelines for trajectory data collection and training data preparation
How to use it
Install
pip install -e ".[seeding,annotator,collection,dev]"From its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up xlyu0106/CUA-Master in my project. Follow its README: https://github.com/xlyu0106/CUA-Master. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/xlyu0106/CUA-Master?ref=badge)Similar repos
- ComputerUseAgent/AutoCua
A Python agent that automates computer tasks on macOS, Windows and Linux, including desktop apps via mouse and keyboard, browsers (Chrome through an extension), shell use in a terminal, and iOS device
- reacher-z/Awesome-CUA
A curated, source-backed catalog of computer-use agent resources, including reviewed papers, GUI models, datasets, benchmarks and tools, with machine-readable JSONL and SQLite data. It also provides l
- Open-RUA/uni-robot-agent
Open-source Python harness for robot-use agents that runs Codex or Claude Code runtimes against simulated robot environments such as RoboDojo, RoboUse and RoboLab. Includes a Python SDK, a local live
- smhanov/agentloop
A Go library that implements the LLM tool-calling loop: it sends prompts to a model, executes requested tool calls, feeds results back, and repeats until a final answer. It adds budgets, hooks, skills
- OpenSparX/MasterAgent
A small C++17 agent runtime that matches exact-phrase skills before calling an optional model, validates tool names and arguments, and runs host-defined tools. Optional SQLite storage records request
- Superone77/TraceVista
A viewer and conversion workflow that turns agent logs from Claude Code, Codex, Pi, InferenceBench and SWE-rebench OpenHands into interactive maps of decisions, phases and actions. Links summaries bac