{"id":35797603,"url":"https://github.com/TurixAI/TuriX-CUA","last_synced_at":"2026-02-25T04:01:13.637Z","repository":{"id":308143423,"uuid":"1031738741","full_name":"TurixAI/TuriX-CUA","owner":"TurixAI","description":"This is the official website for TuriX Computer-use-Agent","archived":false,"fork":false,"pushed_at":"2026-02-13T07:45:16.000Z","size":144570,"stargazers_count":613,"open_issues_count":3,"forks_count":91,"subscribers_count":15,"default_branch":"main","last_synced_at":"2026-02-13T11:50:13.349Z","etag":null,"topics":["agent","ai-agents","browser-use","computer-automation","computer-use","computer-use-agent","cua","gui-agent","gui-operator","mcp","qwen3-vl"],"latest_commit_sha":null,"homepage":"https://turix.ai","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/TurixAI.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":"2025-08-04T08:59:43.000Z","updated_at":"2026-02-13T07:45:19.000Z","dependencies_parsed_at":"2025-09-28T04:06:04.285Z","dependency_job_id":"8ffcbdb3-0921-474f-a259-6c67eb046e1c","html_url":"https://github.com/TurixAI/TuriX-CUA","commit_stats":null,"previous_names":["turixai/turix-cua"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/TurixAI/TuriX-CUA","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TurixAI%2FTuriX-CUA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TurixAI%2FTuriX-CUA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TurixAI%2FTuriX-CUA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TurixAI%2FTuriX-CUA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TurixAI","download_url":"https://codeload.github.com/TurixAI/TuriX-CUA/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TurixAI%2FTuriX-CUA/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29810400,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-25T03:30:18.102Z","status":"ssl_error","status_checked_at":"2026-02-25T03:30:17.799Z","response_time":61,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["agent","ai-agents","browser-use","computer-automation","computer-use","computer-use-agent","cua","gui-agent","gui-operator","mcp","qwen3-vl"],"created_at":"2026-01-07T10:00:54.773Z","updated_at":"2026-02-25T04:01:13.630Z","avatar_url":"https://github.com/TurixAI.png","language":"Python","readme":"\u003cp align=\"center\"\u003e\n   \u003cimg src=\"./doc/LogoHFitted.svg\" width=\"1600\" alt=\"TuriX logo\"\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003eTuriX · Desktop Actions, Driven by AI\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\u003cstrong\u003eTalk to your computer, watch it work.\u003c/strong\u003e\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"README.md\"\u003eEnglish\u003c/a\u003e | \u003ca href=\"README.zh-CN.md\"\u003e中文\u003c/a\u003e\n\u003c/p\u003e\n\n## 📞 Contact \u0026 Community\n\nJoin our Discord community for support, discussions, and updates:\n\n\u003cp align=\"center\"\u003e\n   \u003ca href=\"https://discord.gg/yaYrNAckb5\"\u003e\n      \u003cimg src=\"https://img.shields.io/discord/1400749393841492020?color=7289da\u0026label=Join%20our%20Discord\u0026logo=discord\u0026logoColor=white\u0026style=for-the-badge\" alt=\"Join our Discord\"\u003e\n   \u003c/a\u003e\n\u003c/p\u003e\n\nOr contact us with email: contact@turix.ai\n\nTuriX lets your powerful AI models take real, hands‑on actions directly on your desktop. \nIt ships with a **state‑of‑the‑art computer‑use agent** (passes \u003e 68 % of our internal OSWorld‑style test set) yet stays 100 % open‑source and cost‑free for personal \u0026 research use.  \n\nPrefer your own model? **Change in `config.json` and go.**\n\n## Table of Contents\n- [📞 Contact \u0026 Community](#-contact--community)\n- [🤖 OpenClaw Skill](#-openclaw-skill)\n- [📰 Latest News](#-latest-news)\n- [🖼️ Demos](#️-demos)\n- [✨ Key Features](#-key-features)\n- [📊 Model Performance](#-model-performance)\n- [🚀 Quick‑Start (macOS 15+)](#-quickstart-macos-15)\n   - [1. Download the App](#1-download-the-app)\n   - [2. Create a Python 3.12 Environment](#2-create-a-python-312-environment)\n   - [3. Grant macOS Permissions](#3-grant-macos-permissions)\n      - [3.1 Accessibility](#31-accessibility)\n      - [3.2 Safari Automation](#32-safari-automation)\n   - [4. Configure \u0026 Run](#4-configure--run)\n   - [4.4 Skills (Optional)](#44-skills-optional)\n- [🤝 Contributing](#-contributing)\n- [🗺️ Roadmap](#️-roadmap)\n\n---\n\n## 🤖 OpenClaw Skill\n\nUse TuriX via OpenClaw with our published skill on ClawHub:  \nhttps://clawhub.ai/Tongyu-Yan/turix-cua  \nThis lets OpenClaw call TuriX so it can act as your desktop agent.\n\nLocal OpenCLaw skill (macOS): this repo also includes a ready-to-use skill package in `OpenCLaw_TuriX_skill/` (`SKILL.md` + `scripts/run_turix.sh`).  \nCopy it into your OpenClaw local skills folder (for example: `clawd/skills/local/turix-mac/`) and follow `OpenCLaw_TuriX_skill/README.md` for setup and permissions.\n\n---\n\n## 📰 Latest News\n\n**January 30, 2026** - 🧩 We published the **TuriX OpenClaw Skill** on ClawHub: https://clawhub.ai/Tongyu-Yan/turix-cua. You can now use OpenClaw to call TuriX and automate desktop tasks.\n\n**January 27, 2026 — v0.3** - 🎉 TuriX v0.3 is now live on the main branch! This release brings DuckDuckGo search, Ollama support, advanced recoverable memory compression, and Skills—unlocking smarter planning, more resilient memory, and reusable workflows for desktop automation. We’re excited to see more users try it out and share feedback as we keep pushing the platform forward.\n\n**January 27, 2026** - 🎉 We released **Recoverable Memory Compression** and **Skills** in the `multi-agent` and `multi-agent-windows` branches. These features add more stable memory handling and reusable markdown playbooks for task planning.\n\n**January 27, 2026** - 🎉 We released **Recoverable Memory Compression** and **Skills** in the `main` (formerly `multi-agent`) and `multi-agent-windows` branches. These features add more stable memory handling and reusable markdown playbooks for task planning.\n\n**December 30, 2025** - 🎉 Significant update in Agent Archetecture. We introduce a multi-model archetecture in the `main` (formerly `multi-agent`) branch, releasing the stress from a single model to multiple models.\n\n**October 16, 2025** - 🚀 Big news for automation enthusiasts! TuriX now fully supports the cutting-edge **Qwen3-VL** vision-language model, empowering seamless PC automation across both **macOS** and **Windows**. This integration boosts task success rates by up to 15% on complex UI interactions (based on our internal benchmarks), making your desktop workflows smarter and faster than ever. Whether you're scripting daily routines or tackling intricate projects, Qwen3-VL's advanced multimodal reasoning brings unparalleled precision to the table.\n\n**September 30, 2025** - 🎉 Exciting update! We've just released our latest AI model on the [TuriX API platform](https://turixapi.io), bringing enhanced performance, smarter reasoning, and seamless integration for even more powerful desktop automation. Developers and researchers, this is your cue—head over to the platform to access it now and elevate your workflows!\n\nReady to level up? Update your `config.json` and start automating—happy hacking! 🎉\n\n*Stay tuned to our [Discord](https://discord.gg/vkEYj4EV2n) for tips, user stories, and the next big drop.*\n\n---\n\n## 🖼️ Demos\n\u003ch3 align=\"center\"\u003eMacOS Demo\u003c/h3\u003e\n\u003cp align=\"center\"\u003e\u003cstrong\u003eBook a flight, hotel and uber.\u003c/strong\u003e\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n   \u003cimg src=\"./doc/booking_demo.gif\" width=\"1600\" alt=\"TuriX macOS demo - booking\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\u003cstrong\u003eSearch iPhone price, create Pages document, and send to contact\u003c/strong\u003e\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n   \u003cimg src=\"./doc/demo1.gif\" width=\"1600\" alt=\"TuriX macOS demo - iPhone price search and document sharing\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\u003cstrong\u003eGenerate a bar-chart in the numbers file sent by boss in discord and insert it to the right place of my powerpoint, and reply my boss.\u003c/strong\u003e\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n   \u003cimg src=\"./doc/complex_demo_mac.gif\" width=\"1600\" alt=\"TuriX macOS demo - excel graph to powerpoint\"\u003e\n\u003c/p\u003e\n\n\u003ch3 align=\"center\"\u003eWindows Demo\u003c/h3\u003e\n\u003cp align=\"center\"\u003e\u003cstrong\u003eSearch video content in youtube and like it\u003c/strong\u003e\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n   \u003cimg src=\"./doc/win_demo1.gif\" width=\"1600\" alt=\"TuriX Windows demo - video search and sharing\"\u003e\n\u003c/p\u003e\n\n\u003ch3 align=\"center\"\u003eMCP with Claude Demo\u003c/h3\u003e\n\u003cp align=\"center\"\u003e\u003cstrong\u003eClaude search for AI news, and call TuriX with MCP, write down the research result to a pages document and send it to contact\u003c/strong\u003e\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n   \u003cimg src=\"./doc/mcp_demo1.gif\" width=\"1600\" alt=\"TuriX MCP demo - news search and sharing\"\u003e\n\u003c/p\u003e\n\n---\n\n## ✨ Key Features\n| Capability | What it means |\n|------------|---------------|\n| **SOTA default model** | Outperforms previous open‑source agents (e.g. UI‑TARS) on success rate and speed on Mac |\n| **No app‑specific APIs** | If a human can click it, TuriX can too—WhatsApp, Excel, Outlook, in‑house tools… |\n| **Hot‑swappable \"brains\"** | Replace the VLM policy without touching code (`config.json`) |\n| **MCP‑ready** | Hook up *Claude for Desktop* or **any** agent via the Model Context Protocol (MCP) |\n| **Skills (markdown playbooks)** | Planner selects relevant skill guides (name + description), brain uses full instructions to plan each step |\n\n---\n## 📊 Model Performance\n\nOur agent achieves state-of-the-art performance on desktop automation tasks:\n\u003cp align=\"center\"\u003e\n   \u003cimg src=\"./doc/performance_sum.jpg\" width=\"1600\" alt=\"TuriX performance\"\u003e\n\u003c/p\u003e\n\nFor more details, check our [report](https://turix.ai/technical-report/).\n\n## 🚀 Quick‑Start (macOS 15+)\n\n\u003e **We never collect data**—install, grant permissions, and hack away.\n\n\u003e **0. Windows Users**: Switch to the `multi-agent-windows` branch for Windows-specific setup and installation instructions.\n\u003e\n\u003e ```bash\n\u003e git checkout multi-agent-windows\n\u003e ```\n\u003e\n\u003e **0. Windows Legacy Users**: For the previous Windows setup, switch to the `windows_legacy` branch.\n\u003e\n\u003e **0. macOS Legacy Users**: For the previous single-model macOS setup, switch to the `mac_legacy` branch.\n\n\n### 1. Download the App\nFor easier usage, [download the app](https://turix.ai/)\n\nOr follow the manual setup below:\n\n### 2. Create a Python 3.12 Environment\nFirstly Clone the repository and run:\n```bash\nconda create -n turix_env python=3.12\nconda activate turix_env        # requires conda ≥ 22.9\npip install -r requirements.txt\n```\n\n### 3. Grant macOS Permissions\n\n#### 3.1 Accessibility\n1. Open **System Settings ▸ Privacy \u0026 Security ▸ Accessibility**  \n2. Click **＋**, then add **Terminal** and **Visual Studio Code** ANY IDE you use\n3. If the agent still fails, also add **/usr/bin/python3**\n\n#### 3.2 Safari Automation\n1. **Safari ▸ Settings ▸ Advanced** → enable **Show features for web developers**  \n2. In the new **Develop** menu, enable  \n    * **Allow Remote Automation**  \n    * **Allow JavaScript from Apple Events**  \n\n##### Trigger the Permission Dialogs (run once per shell)\n```\n# macOS Terminal\nosascript -e 'tell application \"Safari\" \\\nto do JavaScript \"alert(\\\"Triggering accessibility request\\\")\" in document 1'\n\n# VS Code integrated terminal (repeat to grant VS Code)\nosascript -e 'tell application \"Safari\" \\\nto do JavaScript \"alert(\\\"Triggering accessibility request\\\")\" in document 1'\n```\n\n\u003e **Click \"Allow\" on every dialog** so the agent can drive Safari.\n\n### 4. Configure \u0026 Run\n\n#### 4.1 Edit Task Configuration\n\n\u003e [!IMPORTANT]\n\u003e **Task Configuration is Critical**: The quality of your task instructions directly impacts success rate. Clear, specific prompts lead to better automation results.\n\nEdit task in `examples/config.json`:\n```json\n{\n    \"agent\": {\n         \"task\": \"open system settings, switch to Dark Mode\"\n    }\n}\n```\n\n#### 4.2 Edit API Configuration\n\nGet API now with $20 credit from our [official web page](https://turix.ai/api-platform/).\nLogin to our website and the key is at the bottom.\n\nIn this main (multi-agent) branch, you need to set the brain, actor, and memory models. It only supports mac for now. If you enable planning\n(`agent.use_plan: true`), you also need to set the planner model.\nWe strongly recommand you to set the turix-actor model as the actor. The brain can be any VLMs you like, we provide qwen3vl in out platform. Gemini-3-pro is tested to be smartest, and Gemini-3-flash is fast and smart enough for most of the tasks.\n\nEdit API in `examples/config.json`:\n```json\n\"brain_llm\": {\n      \"provider\": \"turix\",\n      \"model_name\": \"turix-brain-model\",\n      \"api_key\": \"YOUR_API_KEY\",\n      \"base_url\": \"https://llm.turixapi.io/v1\"\n   },\n\"actor_llm\": {\n      \"provider\": \"turix\",\n      \"model_name\": \"turix-actor-model\",\n      \"api_key\": \"YOUR_API_KEY\",\n      \"base_url\": \"https://llm.turixapi.io/v1\"\n   },\n\"memory_llm\": {\n      \"provider\": \"turix\",\n      \"model_name\": \"turix-memory-model\",\n      \"api_key\": \"YOUR_API_KEY\",\n      \"base_url\": \"https://llm.turixapi.io/v1\"\n   },\n\"planner_llm\": {\n      \"provider\": \"turix\",\n      \"model_name\": \"turix-planner-model\",\n      \"api_key\": \"YOUR_API_KEY\",\n      \"base_url\": \"https://llm.turixapi.io/v1\"\n   }\n```\n\nFor a local Ollama setup, point each role to your Ollama server:\n```json\n\"brain_llm\": {\n      \"provider\": \"ollama\",\n      \"model_name\": \"llama3.2-vision\",\n      \"base_url\": \"http://localhost:11434\"\n   },\n\"actor_llm\": {\n      \"provider\": \"ollama\",\n      \"model_name\": \"llama3.2-vision\",\n      \"base_url\": \"http://localhost:11434\"\n   },\n\"memory_llm\": {\n      \"provider\": \"ollama\",\n      \"model_name\": \"llama3.2-vision\",\n      \"base_url\": \"http://localhost:11434\"\n   },\n\"planner_llm\": {\n      \"provider\": \"ollama\",\n      \"model_name\": \"llama3.2-vision\",\n      \"base_url\": \"http://localhost:11434\"\n   }\n```\n\n#### 4.3 Configure Custom Models (Optional)\n\nIf you want to use other models not defined by the build_llm function in the main.py, you need to first define it, then setup the config.\n\nmain.py:\n\n```\nif provider == \"name_you_want\":\n        return ChatOpenAI(\n            model=\"gpt-4.1-mini\", api_key=api_key, temperature=0.3\n        )\n```\nSwitch between ChatOpenAI, ChatGoogleGenerativeAI, ChatAnthropic, or ChatOllama base on your llm. Also change the model name.\n\n#### 4.4 Skills (Optional)\n\nSkills are lightweight markdown playbooks stored in a single folder (default: `skills/`). Each skill file starts with YAML frontmatter containing `name` and `description`, followed by the instructions. The planner only sees the name + description to select relevant skills; the brain receives the full skill content to guide step goals.\nSkills selection requires planning (`agent.use_plan: true`).\n\nExample skill file (`skills/github-web-actions.md`):\n```md\n---\nname: github-web-actions\ndescription: Use when navigating GitHub in a browser (searching repos, starring, etc.).\n---\n# GitHub Web Actions\n- Open GitHub, use the site search, and navigate to the repo page.\n- If login is required, ask the user before proceeding.\n- Confirm the Star button state before moving on.\n```\n\nEnable in `examples/config.json`:\n```json\n{\n  \"agent\": {\n    \"use_plan\": true,\n    \"use_skills\": true,\n    \"skills_dir\": \"skills\",\n    \"skills_max_chars\": 4000\n  }\n}\n```\n\n#### 4.5 Start the Agent\n\n```bash\npython examples/main.py\n```\n\n**Enjoy hands‑free computing 🎉**\n\n#### 4.6 Resume a Terminated Task\n\nTo resume a task after an interruption, set a stable `agent_id` and enable `resume` in `examples/config.json`:\n```json\n{\n    \"agent\": {\n         \"resume\": true,\n         \"agent_id\": \"my-task-001\"\n    }\n}\n```\nNotes:\n- Use the same `agent_id` as the run you want to resume.\n- Keep the same `task` when resuming.\n- Resume only works if prior memory exists at `src/agent/temp_files/\u003cagent_id\u003e/memory.jsonl`.\n- To start fresh, set `resume` to `false`, change `agent_id`, or delete `src/agent/temp_files/\u003cagent_id\u003e`.\n\n## 🤝 Contributing\n\nWe welcome contributions! Please read our [Contributing Guide](CONTRIBUTING.MD) to get started.\n\nQuick links:\n- [Development Setup](CONTRIBUTING.MD#development-setup)\n- [Code Style Guidelines](CONTRIBUTING.MD#code-style-guidelines)\n- [Testing](CONTRIBUTING.MD#testing)\n- [Pull Request Process](CONTRIBUTING.MD#pull-request-process)\n\nFor bug reports and feature requests, please [open an issue](https://github.com/TurixAI/TuriX-CUA/issues).\n\n## 🗺️ Roadmap\n\n| Quarter | Feature | Description |\n|---------|---------|-------------|\n| **2025 Q3** | **✅ Terminate and Resume** | Support resuming from terminated task. |\n| **2025 Q3** | **✅ Windows Support** | Cross-platform compatibility bringing TuriX automation to Windows environments *(Now Available)* |\n| **2025 Q3** | **✅ Enhanced MCP Integration** | Deeper Model Context Protocol support for seamless third-party agent connectivity *(Now Available)*|\n| **2025 Q4** | **✅ Next-Gen AI Model** | Significantly improved clicking accuracy and task execution capabilities |\n| **2025 Q4** | **✅ Windows-Optimized Model** | Native Windows model architecture for superior performance on Microsoft platforms\n| **2025 Q4** | **✅ Support Gemini-3-pro model** | Run with any compatible vision language models |\n| **2025 Q4** | **✅ Planner** | Understands user intent and makes step-by-step plans to complete tasks |\n| **2025 Q4** | **✅ Multi-Agent Architecture** | Evaluate and guide each step in working |\n| **2025 Q4** | **✅ Duckduckgo Integration** | Speed up the information gathering process, for smarter planning (now on main) |\n| **2026 Q1** | **✅ Ollama Support** | Support the Ollama Qwen3vl models |\n| **2026 Q1** | **✅ Recoverable Memory Compression** | Advance memory management mechanism to stabelize performance (Commited beta version) |\n| **2026 Q1** | **✅ Skills** | Stablize the agent workflow. |\n| **2026 Q1** | **✅ OpenClaw Skill** | Published on ClawHub (https://clawhub.ai/Tongyu-Yan/turix-cua) so OpenClaw can use TuriX as its eyes and hands. |\n| **2026 Q1** | **Browser Automation** | Support a Chrome-like browser for scalability |\n| **2026 Q1** | **Persistent Memory** | Learn user preferences and maintain task history across sessions |\n| **2026 Q2** | **Learning by Demonstration** | Train the agent by showing it your preferred methods and workflows |\n","funding_links":[],"categories":["Python","📚 Projects (2474 total)","🤖️ 二、AI 相关项目"],"sub_categories":["Tools \u0026 Libraries","🧠 2.2 AI 智能体"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTurixAI%2FTuriX-CUA","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTurixAI%2FTuriX-CUA","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTurixAI%2FTuriX-CUA/lists"}