NewWhat happens when hackathon judging is a public benchmark
AComputerComputermacOSWindowsLinuxBrowserPhoneforAIAIAgentMCPAutomationEvalsRL
AI that sees screens, clicks buttons, and types
Just like you — CUA
or Book a Demo
Loved by builders.
AK@_akhaliq
a new computer-use interface on Apple Silicon using local sandboxes by using ai-gradio
無聊就學AI Lab | Boring Traveler@akiraxtwo
CUA 是一個讓電腦能被 AI 真正「操作」的框架，專為 Apple M 系列設計，讓 AI 不只是輸出回答，而是能用滑鼠、鍵盤控制整個系統，甚至看懂畫面。 技術上，它結合 macOS 虛擬機與 Python 控制介面，支援 OpenAI、MLX、Ollama 等主流模型，實現真正的 AI 自動化工作流程。
Tom Dörr@tom_doerr
VM for Agents. Just today, my agent setup broke my computer, preventing disk writing (which also means most programs won't start)
ホーダチ-Hodatsu | LLM Researcher × AI Engineer@hokazuya
これ、最高。 今後絶対的に必要性が上がる、エージェント稼働を容易にMacで実現するための、computer-use、agent、Luma内蔵VMクイックランチャーツール、Cua。 Manus、MCP、エージェントなどを自分のローカルで実行すると、下手をすれば、ぶっ壊れる。…
Nitish Jain
Empowering AEC Designers | AI Product Builder | 3+ Years in Generative Design & Visualization | Speaker & Workshop Leader
🚀 Exciting News in the World of Tech Innovation! 🚀 I just came across an incredible development by @trycua that's pushing the boundaries of how we interact with computers. They've introduced a new computer-use interface built on Apple Silicon, leveraging local sandboxes and AI-powered Gradio to create a seamless, secure, and intuitive user experience. Here's why this is a game-changer: ✨ Local Sandboxes: By running processes in isolated environments, this interface ensures enhanced security and privacy, keeping your data safe while maintaining performance. ✨ Apple Silicon Optimization: Built specifically for Apple's powerful chips, it delivers blazing-fast performance and energy efficiency. ✨ AI-Gradio Integration: The use of Gradio for AI interactions makes the interface incredibly user-friendly, enabling natural and dynamic communication between users and AI systems. This innovation is a testament to how far we've come in reimagining human-computer interaction. It's not just about faster or sleeker tech—it's about creating tools that adapt to us, making technology more accessible and intuitive. Huge kudos to @trycua for their groundbreaking work! I can't wait to see how this evolves and shapes the future of computing. What are your thoughts on this? Let's discuss! 👇
View post on LinkedIn
Adam Silverman (Hiring!) 🖇️@AtomSilverman
Hot take: The only world where browser use / computer use agents are successful at scale is if they are within a VM companies want their employees to work, not watch their agents do work while they relax
Chris Barber@chrisbarber
AI Timelines: When will AI reach human-level in computer-use skills? I surveyed AI researchers and forecasters. I asked: by what quarter & year are you nearly certain (9-in-10 chance) that AI will reach human-level on the OSWorld computer-use benchmark? Surveyed: ,…
Tom Dörr@tom_doerr
What so my IDE now writes code and creates presentations with analysis results? New AI tools seem like April Fools' jokes
Shubham | Agnost AI#laalshaitaan
#generalhey hey, excited to see how cua pans out! loved the product from whatever i could infer ❤️ all the best. a fellow oss contributor, would love to help in anyway possible, lmk if something pops up!
15 Trending AI Projects on GitHub: opcode, FastMCP, Dyad, RustGPT, Paper2Agent, Pepper, AG-UI,shimmy
Github Awesome
Watch video
Suhail@Suhail
This is basically Mighty for AI browser use in the cloud. Guess I'll go back to making a superhuman ai designer.
Adam Silverman (Hiring!) 🖇️@AtomSilverman
3/ The era of local Computer-Use AI Agents is here! introduces UI-TARS-1.5-7B-6bit, now running natively on Apple Silicon via MLX.
Solomon Hykes@solomonstre
OK we may have a path to running native mac builds in ! Thanks to the lume CLI by 😁 I'm thinking we could have the Dagger CLI natively run that, and expose it as a core primitive in the Dagger API. cc
Robert Scoble@Scobleizer
"Control full operating systems."
The Industry Reacts to GPT-5
Matthew Berman
Watch video
Unwind AI@unwind_ai_
2. Build Computer-Use AI Agents that control specific applications. Deploy a team of specialized lightweight agents in parallel, each focused on their own app, like "just control the iPhone Mirroring app."
taruntarun0023
#generalThere's a million things that could be built on top of ollama and a million other things using cua, its the future! Embrace it, and don't forget to enjoy the process, results are just a by-product. These hackthons when done correctly have changed the entire course of one's life, I have personally seen this happen with some of own friends, the network effects, the sense of community and urgency that you experience for these next one week, will literally define your limits, and push you to the edge of safely operational capacity. If you need any help with resources / guidance, i am sure @James will be here to help everyone in any ways possible, he's one of the best in town. If you need anything from my end, to get a second opinion on somethings or even just someone to vent out to i am here, feel free to DM me. And you got this guys! If you are not living on the edge, then you are taking too much space. When you hold a hammer, everything looks like a nail. CUA team has given you the damn hammer go nail it
Adam Silverman (Hiring!) 🖇️@AtomSilverman
9/ GPT-5 for Computer-Use agents. Same tasks, same grounding model - we just swapped GPT-4o → GPT-5 as the thinking model. Left = 4o, right = 5. Watch GPT-5 pull away.
Yoko@stuffyokodraws
[New Post] CUA market and where things are. Below is what it takes to construct a computer use agent today, and some different approaches to get there We are still in the very early innings but and I are excited to hear what you build 🧵
Francesco@francedot
just woke up to find we're #1 trending on GitHub! what a wild ride - and awesome to see 3 YC teams up there together!
Erik Thorelli@esthor
cua is 🔥 and their team is incredible. big congrats and for crushing it on computer use and doing it with OSS👏
Adam Silverman (Hiring!) 🖇️@AtomSilverman
21/ benchmarks Moondream3 against GTA-1. It delivers solid accuracy for open-weight agent models.
Horticolexhorticulture
#generalbest project in the world developers must be both cracked AND handsome can't wait to use it to do all my tasks
AK@_akhaliq
a new computer-use interface on Apple Silicon using local sandboxes by using ai-gradio
無聊就學AI Lab | Boring Traveler@akiraxtwo
CUA 是一個讓電腦能被 AI 真正「操作」的框架，專為 Apple M 系列設計，讓 AI 不只是輸出回答，而是能用滑鼠、鍵盤控制整個系統，甚至看懂畫面。 技術上，它結合 macOS 虛擬機與 Python 控制介面，支援 OpenAI、MLX、Ollama 等主流模型，實現真正的 AI 自動化工作流程。
Tom Dörr@tom_doerr
VM for Agents. Just today, my agent setup broke my computer, preventing disk writing (which also means most programs won't start)
ホーダチ-Hodatsu | LLM Researcher × AI Engineer@hokazuya
これ、最高。 今後絶対的に必要性が上がる、エージェント稼働を容易にMacで実現するための、computer-use、agent、Luma内蔵VMクイックランチャーツール、Cua。 Manus、MCP、エージェントなどを自分のローカルで実行すると、下手をすれば、ぶっ壊れる。…
Nitish Jain
Empowering AEC Designers | AI Product Builder | 3+ Years in Generative Design & Visualization | Speaker & Workshop Leader
🚀 Exciting News in the World of Tech Innovation! 🚀 I just came across an incredible development by @trycua that's pushing the boundaries of how we interact with computers. They've introduced a new computer-use interface built on Apple Silicon, leveraging local sandboxes and AI-powered Gradio to create a seamless, secure, and intuitive user experience. Here's why this is a game-changer: ✨ Local Sandboxes: By running processes in isolated environments, this interface ensures enhanced security and privacy, keeping your data safe while maintaining performance. ✨ Apple Silicon Optimization: Built specifically for Apple's powerful chips, it delivers blazing-fast performance and energy efficiency. ✨ AI-Gradio Integration: The use of Gradio for AI interactions makes the interface incredibly user-friendly, enabling natural and dynamic communication between users and AI systems. This innovation is a testament to how far we've come in reimagining human-computer interaction. It's not just about faster or sleeker tech—it's about creating tools that adapt to us, making technology more accessible and intuitive. Huge kudos to @trycua for their groundbreaking work! I can't wait to see how this evolves and shapes the future of computing. What are your thoughts on this? Let's discuss! 👇
View post on LinkedIn
Adam Silverman (Hiring!) 🖇️@AtomSilverman
Hot take: The only world where browser use / computer use agents are successful at scale is if they are within a VM companies want their employees to work, not watch their agents do work while they relax
Chris Barber@chrisbarber
AI Timelines: When will AI reach human-level in computer-use skills? I surveyed AI researchers and forecasters. I asked: by what quarter & year are you nearly certain (9-in-10 chance) that AI will reach human-level on the OSWorld computer-use benchmark? Surveyed: ,…
Tom Dörr@tom_doerr
What so my IDE now writes code and creates presentations with analysis results? New AI tools seem like April Fools' jokes
Shubham | Agnost AI#laalshaitaan
#generalhey hey, excited to see how cua pans out! loved the product from whatever i could infer ❤️ all the best. a fellow oss contributor, would love to help in anyway possible, lmk if something pops up!
15 Trending AI Projects on GitHub: opcode, FastMCP, Dyad, RustGPT, Paper2Agent, Pepper, AG-UI,shimmy
Github Awesome
Watch video
Suhail@Suhail
This is basically Mighty for AI browser use in the cloud. Guess I'll go back to making a superhuman ai designer.
Adam Silverman (Hiring!) 🖇️@AtomSilverman
3/ The era of local Computer-Use AI Agents is here! introduces UI-TARS-1.5-7B-6bit, now running natively on Apple Silicon via MLX.
Solomon Hykes@solomonstre
OK we may have a path to running native mac builds in ! Thanks to the lume CLI by 😁 I'm thinking we could have the Dagger CLI natively run that, and expose it as a core primitive in the Dagger API. cc
Robert Scoble@Scobleizer
"Control full operating systems."
The Industry Reacts to GPT-5
Matthew Berman
Watch video
Unwind AI@unwind_ai_
2. Build Computer-Use AI Agents that control specific applications. Deploy a team of specialized lightweight agents in parallel, each focused on their own app, like "just control the iPhone Mirroring app."
taruntarun0023
#generalThere's a million things that could be built on top of ollama and a million other things using cua, its the future! Embrace it, and don't forget to enjoy the process, results are just a by-product. These hackthons when done correctly have changed the entire course of one's life, I have personally seen this happen with some of own friends, the network effects, the sense of community and urgency that you experience for these next one week, will literally define your limits, and push you to the edge of safely operational capacity. If you need any help with resources / guidance, i am sure @James will be here to help everyone in any ways possible, he's one of the best in town. If you need anything from my end, to get a second opinion on somethings or even just someone to vent out to i am here, feel free to DM me. And you got this guys! If you are not living on the edge, then you are taking too much space. When you hold a hammer, everything looks like a nail. CUA team has given you the damn hammer go nail it
Adam Silverman (Hiring!) 🖇️@AtomSilverman
9/ GPT-5 for Computer-Use agents. Same tasks, same grounding model - we just swapped GPT-4o → GPT-5 as the thinking model. Left = 4o, right = 5. Watch GPT-5 pull away.
Yoko@stuffyokodraws
[New Post] CUA market and where things are. Below is what it takes to construct a computer use agent today, and some different approaches to get there We are still in the very early innings but and I are excited to hear what you build 🧵
Francesco@francedot
just woke up to find we're #1 trending on GitHub! what a wild ride - and awesome to see 3 YC teams up there together!
Erik Thorelli@esthor
cua is 🔥 and their team is incredible. big congrats and for crushing it on computer use and doing it with OSS👏
Adam Silverman (Hiring!) 🖇️@AtomSilverman
21/ benchmarks Moondream3 against GTA-1. It delivers solid accuracy for open-weight agent models.
Horticolexhorticulture
#generalbest project in the world developers must be both cracked AND handsome can't wait to use it to do all my tasks
AK@_akhaliq
a new computer-use interface on Apple Silicon using local sandboxes by using ai-gradio
無聊就學AI Lab | Boring Traveler@akiraxtwo
CUA 是一個讓電腦能被 AI 真正「操作」的框架，專為 Apple M 系列設計，讓 AI 不只是輸出回答，而是能用滑鼠、鍵盤控制整個系統，甚至看懂畫面。 技術上，它結合 macOS 虛擬機與 Python 控制介面，支援 OpenAI、MLX、Ollama 等主流模型，實現真正的 AI 自動化工作流程。
Tom Dörr@tom_doerr
VM for Agents. Just today, my agent setup broke my computer, preventing disk writing (which also means most programs won't start)
ホーダチ-Hodatsu | LLM Researcher × AI Engineer@hokazuya
これ、最高。 今後絶対的に必要性が上がる、エージェント稼働を容易にMacで実現するための、computer-use、agent、Luma内蔵VMクイックランチャーツール、Cua。 Manus、MCP、エージェントなどを自分のローカルで実行すると、下手をすれば、ぶっ壊れる。…
Nitish Jain
Empowering AEC Designers | AI Product Builder | 3+ Years in Generative Design & Visualization | Speaker & Workshop Leader
🚀 Exciting News in the World of Tech Innovation! 🚀 I just came across an incredible development by @trycua that's pushing the boundaries of how we interact with computers. They've introduced a new computer-use interface built on Apple Silicon, leveraging local sandboxes and AI-powered Gradio to create a seamless, secure, and intuitive user experience. Here's why this is a game-changer: ✨ Local Sandboxes: By running processes in isolated environments, this interface ensures enhanced security and privacy, keeping your data safe while maintaining performance. ✨ Apple Silicon Optimization: Built specifically for Apple's powerful chips, it delivers blazing-fast performance and energy efficiency. ✨ AI-Gradio Integration: The use of Gradio for AI interactions makes the interface incredibly user-friendly, enabling natural and dynamic communication between users and AI systems. This innovation is a testament to how far we've come in reimagining human-computer interaction. It's not just about faster or sleeker tech—it's about creating tools that adapt to us, making technology more accessible and intuitive. Huge kudos to @trycua for their groundbreaking work! I can't wait to see how this evolves and shapes the future of computing. What are your thoughts on this? Let's discuss! 👇
View post on LinkedIn
Adam Silverman (Hiring!) 🖇️@AtomSilverman
Hot take: The only world where browser use / computer use agents are successful at scale is if they are within a VM companies want their employees to work, not watch their agents do work while they relax
Chris Barber@chrisbarber
AI Timelines: When will AI reach human-level in computer-use skills? I surveyed AI researchers and forecasters. I asked: by what quarter & year are you nearly certain (9-in-10 chance) that AI will reach human-level on the OSWorld computer-use benchmark? Surveyed: ,…
Tom Dörr@tom_doerr
What so my IDE now writes code and creates presentations with analysis results? New AI tools seem like April Fools' jokes
Shubham | Agnost AI#laalshaitaan
#generalhey hey, excited to see how cua pans out! loved the product from whatever i could infer ❤️ all the best. a fellow oss contributor, would love to help in anyway possible, lmk if something pops up!
15 Trending AI Projects on GitHub: opcode, FastMCP, Dyad, RustGPT, Paper2Agent, Pepper, AG-UI,shimmy
Github Awesome
Watch video
Suhail@Suhail
This is basically Mighty for AI browser use in the cloud. Guess I'll go back to making a superhuman ai designer.
Adam Silverman (Hiring!) 🖇️@AtomSilverman
3/ The era of local Computer-Use AI Agents is here! introduces UI-TARS-1.5-7B-6bit, now running natively on Apple Silicon via MLX.
Solomon Hykes@solomonstre
OK we may have a path to running native mac builds in ! Thanks to the lume CLI by 😁 I'm thinking we could have the Dagger CLI natively run that, and expose it as a core primitive in the Dagger API. cc
Robert Scoble@Scobleizer
"Control full operating systems."
The Industry Reacts to GPT-5
Matthew Berman
Watch video
Unwind AI@unwind_ai_
2. Build Computer-Use AI Agents that control specific applications. Deploy a team of specialized lightweight agents in parallel, each focused on their own app, like "just control the iPhone Mirroring app."
taruntarun0023
#generalThere's a million things that could be built on top of ollama and a million other things using cua, its the future! Embrace it, and don't forget to enjoy the process, results are just a by-product. These hackthons when done correctly have changed the entire course of one's life, I have personally seen this happen with some of own friends, the network effects, the sense of community and urgency that you experience for these next one week, will literally define your limits, and push you to the edge of safely operational capacity. If you need any help with resources / guidance, i am sure @James will be here to help everyone in any ways possible, he's one of the best in town. If you need anything from my end, to get a second opinion on somethings or even just someone to vent out to i am here, feel free to DM me. And you got this guys! If you are not living on the edge, then you are taking too much space. When you hold a hammer, everything looks like a nail. CUA team has given you the damn hammer go nail it
Adam Silverman (Hiring!) 🖇️@AtomSilverman
9/ GPT-5 for Computer-Use agents. Same tasks, same grounding model - we just swapped GPT-4o → GPT-5 as the thinking model. Left = 4o, right = 5. Watch GPT-5 pull away.
Yoko@stuffyokodraws
[New Post] CUA market and where things are. Below is what it takes to construct a computer use agent today, and some different approaches to get there We are still in the very early innings but and I are excited to hear what you build 🧵
Francesco@francedot
just woke up to find we're #1 trending on GitHub! what a wild ride - and awesome to see 3 YC teams up there together!
Erik Thorelli@esthor
cua is 🔥 and their team is incredible. big congrats and for crushing it on computer use and doing it with OSS👏
Adam Silverman (Hiring!) 🖇️@AtomSilverman
21/ benchmarks Moondream3 against GTA-1. It delivers solid accuracy for open-weight agent models.
Horticolexhorticulture
#generalbest project in the world developers must be both cracked AND handsome can't wait to use it to do all my tasks
AK@_akhaliq
a new computer-use interface on Apple Silicon using local sandboxes by using ai-gradio
無聊就學AI Lab | Boring Traveler@akiraxtwo
CUA 是一個讓電腦能被 AI 真正「操作」的框架，專為 Apple M 系列設計，讓 AI 不只是輸出回答，而是能用滑鼠、鍵盤控制整個系統，甚至看懂畫面。 技術上，它結合 macOS 虛擬機與 Python 控制介面，支援 OpenAI、MLX、Ollama 等主流模型，實現真正的 AI 自動化工作流程。
Tom Dörr@tom_doerr
VM for Agents. Just today, my agent setup broke my computer, preventing disk writing (which also means most programs won't start)
ホーダチ-Hodatsu | LLM Researcher × AI Engineer@hokazuya
これ、最高。 今後絶対的に必要性が上がる、エージェント稼働を容易にMacで実現するための、computer-use、agent、Luma内蔵VMクイックランチャーツール、Cua。 Manus、MCP、エージェントなどを自分のローカルで実行すると、下手をすれば、ぶっ壊れる。…
Nitish Jain
Empowering AEC Designers | AI Product Builder | 3+ Years in Generative Design & Visualization | Speaker & Workshop Leader
🚀 Exciting News in the World of Tech Innovation! 🚀 I just came across an incredible development by @trycua that's pushing the boundaries of how we interact with computers. They've introduced a new computer-use interface built on Apple Silicon, leveraging local sandboxes and AI-powered Gradio to create a seamless, secure, and intuitive user experience. Here's why this is a game-changer: ✨ Local Sandboxes: By running processes in isolated environments, this interface ensures enhanced security and privacy, keeping your data safe while maintaining performance. ✨ Apple Silicon Optimization: Built specifically for Apple's powerful chips, it delivers blazing-fast performance and energy efficiency. ✨ AI-Gradio Integration: The use of Gradio for AI interactions makes the interface incredibly user-friendly, enabling natural and dynamic communication between users and AI systems. This innovation is a testament to how far we've come in reimagining human-computer interaction. It's not just about faster or sleeker tech—it's about creating tools that adapt to us, making technology more accessible and intuitive. Huge kudos to @trycua for their groundbreaking work! I can't wait to see how this evolves and shapes the future of computing. What are your thoughts on this? Let's discuss! 👇
View post on LinkedIn
Adam Silverman (Hiring!) 🖇️@AtomSilverman
Hot take: The only world where browser use / computer use agents are successful at scale is if they are within a VM companies want their employees to work, not watch their agents do work while they relax
Chris Barber@chrisbarber
AI Timelines: When will AI reach human-level in computer-use skills? I surveyed AI researchers and forecasters. I asked: by what quarter & year are you nearly certain (9-in-10 chance) that AI will reach human-level on the OSWorld computer-use benchmark? Surveyed: ,…
Tom Dörr@tom_doerr
What so my IDE now writes code and creates presentations with analysis results? New AI tools seem like April Fools' jokes
Shubham | Agnost AI#laalshaitaan
#generalhey hey, excited to see how cua pans out! loved the product from whatever i could infer ❤️ all the best. a fellow oss contributor, would love to help in anyway possible, lmk if something pops up!
15 Trending AI Projects on GitHub: opcode, FastMCP, Dyad, RustGPT, Paper2Agent, Pepper, AG-UI,shimmy
Github Awesome
Watch video
Suhail@Suhail
This is basically Mighty for AI browser use in the cloud. Guess I'll go back to making a superhuman ai designer.
Adam Silverman (Hiring!) 🖇️@AtomSilverman
3/ The era of local Computer-Use AI Agents is here! introduces UI-TARS-1.5-7B-6bit, now running natively on Apple Silicon via MLX.
Solomon Hykes@solomonstre
OK we may have a path to running native mac builds in ! Thanks to the lume CLI by 😁 I'm thinking we could have the Dagger CLI natively run that, and expose it as a core primitive in the Dagger API. cc
Robert Scoble@Scobleizer
"Control full operating systems."
The Industry Reacts to GPT-5
Matthew Berman
Watch video
Unwind AI@unwind_ai_
2. Build Computer-Use AI Agents that control specific applications. Deploy a team of specialized lightweight agents in parallel, each focused on their own app, like "just control the iPhone Mirroring app."
taruntarun0023
#generalThere's a million things that could be built on top of ollama and a million other things using cua, its the future! Embrace it, and don't forget to enjoy the process, results are just a by-product. These hackthons when done correctly have changed the entire course of one's life, I have personally seen this happen with some of own friends, the network effects, the sense of community and urgency that you experience for these next one week, will literally define your limits, and push you to the edge of safely operational capacity. If you need any help with resources / guidance, i am sure @James will be here to help everyone in any ways possible, he's one of the best in town. If you need anything from my end, to get a second opinion on somethings or even just someone to vent out to i am here, feel free to DM me. And you got this guys! If you are not living on the edge, then you are taking too much space. When you hold a hammer, everything looks like a nail. CUA team has given you the damn hammer go nail it
Adam Silverman (Hiring!) 🖇️@AtomSilverman
9/ GPT-5 for Computer-Use agents. Same tasks, same grounding model - we just swapped GPT-4o → GPT-5 as the thinking model. Left = 4o, right = 5. Watch GPT-5 pull away.
Yoko@stuffyokodraws
[New Post] CUA market and where things are. Below is what it takes to construct a computer use agent today, and some different approaches to get there We are still in the very early innings but and I are excited to hear what you build 🧵
Francesco@francedot
just woke up to find we're #1 trending on GitHub! what a wild ride - and awesome to see 3 YC teams up there together!
Erik Thorelli@esthor
cua is 🔥 and their team is incredible. big congrats and for crushing it on computer use and doing it with OSS👏
Adam Silverman (Hiring!) 🖇️@AtomSilverman
21/ benchmarks Moondream3 against GTA-1. It delivers solid accuracy for open-weight agent models.
Horticolexhorticulture
#generalbest project in the world developers must be both cracked AND handsome can't wait to use it to do all my tasks
Integrate
Computer Use Stack
One unified interface for computer use models. Execute powerful workflows with structured outputs, multi-turn conversations, and custom tools.
Choose your integration
Agent SDK
Python
Build AI agents that automate workflows on Cua Computers
pip install cua-agentMCP Server
Model Context Protocol
Run CUA through Claude Desktop or other MCP clients
pip install cua-mcp-serverfrom agent import ComputerAgent
from computer import Computer
# Initialize local Docker computer
computer = Computer(
os_type="linux",
provider_type="docker",
name="trycua/cua-ubuntu:latest"
)
# Initialize agent with model and tools
agent = ComputerAgent(
model="anthropic/claude-sonnet-4-5-20250929",
tools=[computer]
)
# Run agent with task
messages = [{"role": "user", "content": "Take a screenshot"}]
async for result in agent.run(messages):
print(result)Ship and Scale
Ship and Scale Fast
Cloud-powered sandboxes for your computer use agents. Simple API integration, unlimited scale.
Simple integration
Just plug in your API key to the cua-agent SDK and start running cloud sandboxes instantly
config.py
from cua import Computer
computer = Computer(
provider_type="cloud",
api_key="cua_****"
)
Scale Effortlessly
Run as many sandboxes as you need. No infrastructure management, no resource limits
Active
Active
Active
Active
Cross-platform
Choose between Linux and Windows sandboxes based on your automation needs
Cloud VLM Inference
Access 100+ vision-language models from top providers with one API key
Pay-as-you-go
Only pay for what you use. Credit-based billing with no upfront costs or monthly minimums
Smart auto-routing
Automatically route requests to the best model for your task, balancing performance and cost
Open source
Agent SDK, Computer SDK, macOS virtualization, and Docker images. All open source on GitHub
Benchmark and RL
Train, Evaluate and Improve
Built-in tools for benchmarking agent performance and reinforcement learning. Iterate faster with data-driven insights.
Benchmark suite
Run standardized benchmarks to measure agent performance across different tasks and environments
Task 1
85%
Task 2
72%
Task 3
91%
Task 4
68%
Task 5
79%
RL training
Train agents with reinforcement learning. Automatically optimize behavior through trial and feedback
RewardEpisode 1000
0Episodes
Performance metrics
Track success rates, execution time, and resource usage. Identify bottlenecks and optimize workflows
94%
Success Rate
2.3s
Avg Time
1.2k
Tasks Run
12MB
Memory
A/B testing
Compare different agent configurations, prompts, and models to find the optimal setup
A
Config A
87%
Success
B
Config B
94%
Success
Dataset management
Organize test cases, training data, and evaluation datasets in one place for reproducible experiments
Continuous evaluation
Automatically run benchmarks on every code change. Catch performance regressions before deployment
Export & share
Export results as JSON, CSV, or interactive reports. Share benchmark results with your team
Pricing
Choose the plan that works for you.
Open Source
Free
For developers and open-source projects who prefer self-hosting.
- MIT License
- Windows, Linux, macOS local environments
- 100+ VLMs in Cua Agent Framework
- Community Discord
Most Popular
Pro
$10+
Flexible credits for cloud compute and Computer-Use VLMs, with managed cloud environments and inference.
- Cloud Linux and Windows Environments
- CUA LLM Inference Provider
- Cuazar Playground UI
- Priority support via Slack
$
Enterprise
Custom monthly
Scalable cloud containers tailored for large teams and organizations.
- Everything in Pro
- 24/7 support
- HIPAA, SOC Type 1/2 Reports