{"id":50675168,"url":"https://github.com/ziuus/ui-agent","last_synced_at":"2026-06-08T15:02:30.383Z","repository":{"id":359285244,"uuid":"1215722140","full_name":"ziuus/ui-agent","owner":"ziuus","description":"Vision-assisted desktop automation CLI for computer-use experiments.","archived":false,"fork":false,"pushed_at":"2026-05-21T06:47:18.000Z","size":64,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-05-21T13:36:49.695Z","etag":null,"topics":["collaborate","github-copilot"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ziuus.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-20T07:34:17.000Z","updated_at":"2026-05-21T06:49:35.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ziuus/ui-agent","commit_stats":null,"previous_names":["ziuus/ui-agent"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/ziuus/ui-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziuus%2Fui-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziuus%2Fui-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziuus%2Fui-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziuus%2Fui-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ziuus","download_url":"https://codeload.github.com/ziuus/ui-agent/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziuus%2Fui-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34067353,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-08T02:00:07.615Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["collaborate","github-copilot"],"created_at":"2026-06-08T15:02:26.343Z","updated_at":"2026-06-08T15:02:30.374Z","avatar_url":"https://github.com/ziuus.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🖱️ UI Agent\n\n\u003e **Autonomous Desktop Automation — A vision-powered agentic CLI for intelligent \"Computer Use\" and UI orchestration.**\n\nUI Agent is a production-ready, high-fidelity automation tool that bridges the gap between natural language intent and native desktop interaction. By leveraging **Gemini-1.5 Flash Vision**, it autonomously navigates, clicks, and types within any local application, providing a zero-friction interface for complex multi-app workflows and system management.\n\n## ⚡ Core Features\n\n- **Vision-Powered Detection**: Describe any UI element in natural language (\"the blue submit button in the top right\") and let the AI resolve exact coordinates via real-time screen analysis.\n- **Agentic Orchestration**: High-fidelity execution of mouse and keyboard events with configurable kinetic delays and safety failsafes.\n- **Multi-OS Intelligence**: Native support for Linux, Windows, and macOS with resolution-aware coordinate mapping.\n- **Professional CLI**: Polished terminal interface powered by `typer` and `rich`, complete with status indicators, spinners, and formatted tables.\n- **Safety First**: Integrated fail-safe protocols—instantly abort any action by moving the mouse to a screen corner.\n\n## 🛠 Tech Stack\n\n- **Engine**: Python 3.10+\n- **Intelligence**: Google Gemini-1.5 Flash (Vision API)\n- **Automation**: PyAutoGUI + MSS (Screen Capture)\n- **CLI**: Typer + Rich\n- **Packaging**: Modern PEP 517/518 standards\n\n## 🚀 Getting Started\n\n1. **Global Installation**:\n   ```bash\n   pip install .\n   ```\n\n2. **Configure Environment**:\n   ```bash\n   export GEMINI_API_KEY=\"your_key_here\"\n   ```\n\n3. **Execute Command**:\n   ```bash\n   ui-agent click \"Open the web browser\"\n   ```\n\n## 📂 Project Structure\n\n- `ui_agent/cli.py`: Primary command interface and logic.\n- `ui_agent/vision.py`: Gemini Vision integration and element detection.\n- `ui_agent/automator.py`: Kinetic mouse and keyboard control.\n\n---\n*UI Agent: Connecting Human Intent to Machine Execution.*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fziuus%2Fui-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fziuus%2Fui-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fziuus%2Fui-agent/lists"}