TuriX AI Launches Latest Version of Open-Source Computer-Use Agent

Notifications You must be signed in to change notification settings

Fork 305

Star 3k

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

228 Commits

228 Commits

OpenCLaw_TuriX_skill

OpenCLaw_TuriX_skill

doc

doc

examples

examples

skills

skills

src

src

.gitignore

.gitignore

CONTRIBUTING.MD

CONTRIBUTING.MD

LICENSE

LICENSE

README.md

README.md

README.zh-CN.md

README.zh-CN.md

requirements.txt

requirements.txt

Repository files navigation

Talk to your computer, watch it work.

English | 中文

📞 Contact & Community

Join our Discord community for support, discussions, and updates:

Or contact us with email: [email protected]

TuriX lets your powerful AI models take real, hands‑on actions directly on your desktop. It ships with a state‑of‑the‑art computer‑use agent (achieves 80% success rate on our OSWorld‑style Mac benchmark and 64.2% success rate on OSWorld) yet stays 100 % open‑source and cost‑free for personal & research use.

Prefer your own model? Change in config.json and go.

Table of Contents

📞 Contact & Community

🤖 OpenClaw Skill

📰 Latest News

🖼️ Demos

✨ Key Features

📊 Model Performance

🚀 Quick‑Start (macOS 15+)

1. Download the App

1. Create a Python 3.12 Environment

1. Grant macOS Permissions

3.1 Accessibility

3.2 Safari Automation

1. Configure & Run

4.4 Skills (Optional)

🤝 Contributing

🗺️ Roadmap

🤖 OpenClaw Skill

Use TuriX via OpenClaw with our published ClawHub skill:

https://clawhub.ai/Tongyu-Yan/turix-cua

This repo also includes local OpenClaw skill packages in OpenCLaw_TuriX_skill/:

macOS package in main (SKILL.md + scripts/run_turix.sh)

Windows package in multi-agent-windows (SKILL.md + scripts/run_turix.ps1 + agents/openai.yaml)

For installation and permissions, follow OpenCLaw_TuriX_skill/README.md.

📰 Latest News

May 11, 2026 - Now can download TuriX SuperAgent from our official web page.

April 8, 2026 - 🚀 Introducing TuriX SuperPower 3.0.0-alpha for macOS (Apple Silicon)

This is our all-in-one productivity app that combines TuriX CUA + CLI in one workflow, and adds two new capabilities:

TuriX-work for everyday office execution and task orchestration

TuriX-code for coding, automation, and engineering tasks

From writing code to handling office tasks, you can execute with CLI precision and close the loop through GUI actions in one continuous flow.

March 16, 2026 - 🐧 Linux support is now available on branch multi-agent-linux. If you want to run TuriX on Linux (for example Ubuntu), switch to that branch first:

git checkout multi-agent-linux

March 9, 2026 - Added a new OpenClaw Flash/Fast Mode skill for macOS on branch mac_legacy. If you want to use this faster, lighter setup, switch to that branch first:

git checkout mac_legacy

March 5, 2026 - Updated the Windows OpenClaw local skill on branch multi-agent-windows with direct dispatch, safer pre-flight checks, and the new OpenCLaw_TuriX_skill/agents/openai.yaml.

Earlier updates (Jan 2026 and before) - We shipped v0.3 (DuckDuckGo, Ollama, recoverable memory compression, Skills), published the TuriX OpenClaw skill on ClawHub, upgraded the core architecture to multi-model, and rolled out major model capability improvements including Qwen3-VL support and TuriX API model upgrades.

Ready to level up? Update your config.json and start automating—happy hacking! 🎉

Stay tuned to our Discord for tips, user stories, and the next big drop.

🖼️ Demos

TuriX SuperPower App Demo

MacOS Demo

Book a flight, hotel and uber.

Search iPhone price, create Pages document, and send to contact

Generate 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.

Windows Demo

Search video content in youtube and like it

MCP with Claude Demo

Claude search for AI news, and call TuriX with MCP, write down the research result to a pages document and send it to contact

✨ Key Features

Capability What it means

SOTA default model Outperforms previous open‑source agents (e.g. UI‑TARS) on success rate and speed on Mac

No app‑specific APIs If a human can click it, TuriX can too—WhatsApp, Excel, Outlook, in‑house tools…

Hot‑swappable "brains" Replace the VLM policy without touching code (config.json)

MCP‑ready Hook up Claude for Desktop or any agent via the Model Context Protocol (MCP)

Skills (markdown playbooks) Planner selects relevant skill guides (name + description), brain uses full instructions to plan each step

📊 Model Performance

Our agent achieves state-of-the-art performance on desktop automation tasks:

OSWorld Benchmark — 3rd Place on the Leaderboard (50 Steps)

TuriX scores 64.2% (229.88 / 358) on the full OSWorld benchmark, ranking 3rd overall among all submitted agents. Notably, TuriX is built and optimized for macOS, where we achieve an 80%+ success rate on our self-hosted OSWorld-style Mac benchmark. We used zero Linux training data, yet still achieve a top-3 finish on OSWorld's Linux-based environment.

For more details, check our report.

🚀 Quick‑Start (macOS 15+)

We never collect data—install, grant permissions, and hack away.

1. Windows Users: Switch to the multi-agent-windows branch for Windows-specific setup and installation instructions.

git checkout multi-agent-windows

For the updated OpenClaw Windows local skill package, see OpenCLaw_TuriX_skill/README.md in that branch.

1. Linux Users: Switch to the multi-agent-linux branch for Linux-specific setup and installation instructions.

git checkout multi-agent-linux

1. Windows Legacy Users: For the previous Windows setup, switch to the windows_legacy branch.

1. macOS Legacy Users: For the previous single-model macOS setup, switch to the mac_legacy branch.

1. Download the App

For easier usage, download the app

Or follow the manual setup below:

1. Create a Python 3.12 Environment

Firstly Clone the repository and run:

conda create -n turix_env python=3.12 conda activate turix_env # requires conda ≥ 22.9 pip install -r requirements.txt

1. Grant macOS Permissions

3.1 Accessibility

Open System Settings ▸ Privacy & Security ▸ Accessibility

Click ＋, then add Terminal and Visual Studio Code ANY IDE you use

If the agent still fails, also add /usr/bin/python3

3.2 Safari Automation

Safari ▸ Settings ▸ Advanced → enable Show features for web developers

In the new Develop menu, enable

Allow Remote Automation

Allow JavaScript from Apple Events

Trigger the Permission Dialogs (run once per shell)

macOS Terminal

osascript -e 'tell application "Safari" \ to do JavaScript "alert(\"Triggering accessibility request\")" in document 1'

VS Code integrated terminal (repeat to grant VS Code)

osascript -e 'tell application "Safari" \ to do JavaScript "alert(\"Triggering accessibility request\")" in document 1'

Click "Allow" on every dialog so the agent can drive Safari.

1. Configure & Run

4.1 Edit Task Configuration

Important

Task Configuration is Critical: The quality of your task instructions directly impacts success rate. Clear, specific prompts lead to better automation results.

Edit task in examples/config.json:

{ "agent": { "task": "open system settings, switch to Dark Mode" } }

4.2 Edit API Configuration

Get API now with credit from our official web page. Login to our website and the key is at the bottom.

In 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 (agent.use_plan: true), you also need to set the planner model. We strongly recommand you to set the turix-actor model as the actor. The brain can be any VLMs you like, we provide qwen3.5vl in our platform. Gemini-3-pro is tested to be smartest, and Gemini-3-flash is fast and smart enough for most of the tasks.

Edit API in examples/config.json:

"brain_llm": { "provider": "turix", "model_name": "turix-brain", "api_key": "YOUR_API_KEY", "base_url": "https://turixapi.io/v1" }, "actor_llm": { "provider": "turix", "model_name": "turix-actor", "api_key": "YOUR_API_KEY", "base_url": "https://turixapi.io/v1" }, "memory_llm": { "provider": "turix", "model_name": "turix-brain", "api_key": "YOUR_API_KEY", "base_url": "https://turixapi.io/v1" }, "planner_llm": { "provider": "turix", "model_name": "turix-brain", "api_key": "YOUR_API_KEY", "base_url": "https://turixapi.io/v1" }

For a local Ollama setup, point each role to your Ollama server:

"brain_llm": { "provider": "ollama", "model_name": "llama3.2-vision", "base_url": "http://localhost:11434" }, "actor_llm": { "provider": "ollama", "model_name": "llama3.2-vision", "base_url": "http://localhost:11434" }, "memory_llm": { "provider": "ollama", "model_name": "llama3.2-vision", "base_url": "http://localhost:11434" }, "planner_llm": { "provider": "ollama", "model_name": "llama3.2-vision", "base_url": "http://localhost:11434" }

4.3 Configure Custom Models (Optional)

If 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.

main.py:

if provider == "name_you_want": return ChatOpenAI( model="gpt-4.1-mini", api_key=api_key, temperature=0.3 )

Switch between ChatOpenAI, ChatGoogleGenerativeAI, ChatAnthropic, or ChatOllama base on your llm. Also change the model name.

4.4 Skills (Optional)

Skills 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. Skills selection requires planning (agent.use_plan: true).

Example skill file (skills/github-web-actions.md):

--- name: github-web-actions description: Use when navigating GitHub in a browser (searching repos, starring, etc.). ---

GitHub Web Actions

• Open GitHub, use the site search, and navigate to the repo page.
• If login is required, ask the user before proceeding.
• Confirm the Star button state before moving on.

Enable in examples/config.json:

{ "agent": { "use_plan": true, "use_skills": true, "skills_dir": "skills", "skills_max_chars": 4000 } }

4.5 Start the Agent

python examples/main.py

Enjoy hands‑free computing 🎉

4.6 Resume a Terminated Task

To resume a task after an interruption, set a stable agent_id and enable resume in examples/config.json:

{ "agent": { "resume": true, "agent_id": "my-task-001" } }

Notes:

Use the same agent_id as the run you want to resume.

Keep the same task when resuming.

Resume only works if prior memory exists at src/agent/temp_files//memory.jsonl.

To start fresh, set resume to false, change agent_id, or delete src/agent/temp_files/.

🤝 Contributing

We welcome contributions! Please read our Contributing Guide to get started.

Quick links:

Development Setup

Code Style Guidelines

Testing

Pull Request Process

For bug reports and feature requests, please open an issue.

About

This is the official website for TuriX Computer-use-Agent

turix.ai

Topics

agent

mcp

cua

ai-agents

computer-automation

computer-use

gui-agent

browser-use

computer-use-agent

gui-operator

qwen3-vl

Resources

Readme

License

MIT license

Contributing

Contributing

Uh oh!

There was an error while loading. Please reload this page.

Activity

Custom properties

Stars

3k stars

Watchers

24 watching

Forks

305 forks

Report repository

Releases 4

v0.4

Latest

Mar 6, 2026

+ 3 releases

Packages 0

Uh oh!

There was an error while loading. Please reload this page.

Contributors

Uh oh!

There was an error while loading. Please reload this page.

Languages

Python 98.0%

Shell 2.0%