Mano-P 1.0

GUI-Aware Agent Model for Edge Devices

AI for Personal

中文 | English

Overview

Mano-P: "Mano" means "hand" in Spanish, and "P" has dual meanings: Person and Party. We believe that both individuals and organizations can create their own personalized AI, and a bright future of human-machine collaboration is on the horizon.

Mano-P is a GUI-VLA agent project designed specifically for edge devices. It serves both as an open-source project and a hardware product solution. As an open-source project, Mano-P is being released in a phased, progressive manner, targeting three distinct groups of developers. In the first phase, we will open-source the Mano-CUA Skills. This phase is aimed at Agent enthusiasts—such as users of OpenClaw or Claude Code—enabling them to leverage the capabilities of Mano-CUA Skills to construct more intelligent CUA task workflows and overcome the bottlenecks associated with human intervention. In the second phase, we will open-source the local-side models and SDK components of Mano-CUA. This phase targets developers with high security requirements, allowing them to directly utilize GUI-VLA models capable of running inference locally on a Mac mini to build their own custom Skills, Tools, and more; crucially, all your CUA operations will be executed entirely on your local Mac mini and will not be uploaded to external servers. In the third phase, we will open-source the training methodologies and the pruning and quantization techniques used for the Mano-P models. This phase is designed for developers with specific model training needs, empowering them to apply our training methods to create their own on-device GUI-VLA models tailored to their unique requirements.

Regarding our GUI-VLA models—which are capable of running inference directly on Mac mini and MacBook devices—we currently support two deployment methods: First, direct deployment on Mac mini or MacBook models equipped with an M4 chip and 32GB or more of RAM; and second, deployment utilizing a compute stick connected via a USB 4.0 port or higher. We will be releasing detailed instructions for both deployment methods in the near future, and we plan to expand our support to include additional deployment options in the future.

Main Capabilities

Complex GUI Automation: Autonomously complete complex interface operations containing hundreds of interactive elements
Cross-System Data Integration: Extract and integrate multi-source data through pure visual interaction without API interfaces
Long-Task Planning Execution: Support enterprise-level business process automation of dozens to hundreds of steps
Intelligent Report Generation: Automatically generate structured documents such as data analysis reports and work summaries

Technical Background

Mano-P builds upon the complete technical framework of the Mano project (see Mano Technical Report), employing the Mano-Action bidirectional self-reinforcement learning method, three-stage progressive training (SFT → Offline Reinforcement Learning → Online Reinforcement Learning), "think-act-verify" loop reasoning mechanism, and a closed-loop data circulation system to achieve high-precision GUI understanding and operation capabilities. The edge version is optimized through mixed-precision quantization, visual token pruning, and edge inference adaptation, enabling large-scale parameter models to run efficiently on edge devices like Mac mini/MacBook/computing sticks.

🎯 Key Highlights

#1 on OSWorld Benchmark: Mano-P 1.0-72B achieves 58.2% success rate on OSWorld, ranking first among all specialized GUI agent models, outperforming the second-place opencua-72b (45.0%) by 13.2 percentage points
Leading on WebRetriever Protocol I: Mano-P 1.0 scores 41.7 NavEval, surpassing Gemini 2.5 Pro Computer Use (40.9) and Claude 4.5 Computer Use (31.3)
Fully Local Execution: Runs inference locally on Apple M4 chip with 32GB RAM (Mac mini or MacBook). No cloud API calls required. All screenshots and task data stay on-device
High-Performance Inference: The 4B quantized model (w4a16) achieves 476 tokens/s prefill and 76 tokens/s decode on Apple M4 Pro, with only 4.3GB peak memory usage
Autonomous Long-Task Execution: Supports complex business processes with end-to-end automation without internet connectivity

🎬 Use Case Demonstrations

Scenario 1: Mano-afk Fully automated application construction

Mano-P_AFK_EN.mp4

We demonstrated the fully automated application construction process of mano afk. After receiving natural language requirements, the system sequentially completes requirement clarification, technical architecture design, code generation, local deployment, and multi-level testing (API interface testing, LLM based page visual inspection, and end-to-end GUI automation testing driven by VLA model). When the test fails, the system automatically locates the root cause of the problem, fixes the code, and deploys verification again, iterating until all test cases pass. The entire process does not require manual intervention, and ultimately delivers a runnable application with complete requirement documents and build reports.

Scenario 2: Commercial video intelligent system

Mano-P.Commercial_video_intelligent_system_EN.mp4

We fully demonstrated the actual workflow of a commercial video intelligent system. Starting from the user's command, the system automatically completes the entire process of video generation, uploading, analysis, editing, and secondary evaluation. During the process, the system can autonomously operate web pages and editing software, complete fine operations such as file processing and subtitle modification, and generate analysis reports containing subjective evaluations and objective indicators. By comparing the differences between the initial and refined versions, visually present the overall capabilities and application effects of the system.

Scenario 3: Local model task execution

Mano-P._EN.mp4

Mano-P, The small-sized end side GUI-VLA model can run directly on your computer, supporting direct inference operation on Macmini/Macbook with M4 chip and above, as well as direct operation on plug and play computing power sticks. In the CUA scenario, break through the bottleneck of human participation in the Agent workflow. Mano-P, The first step in leading AI for Personal/Party.

Scenario 4: Daily Life and Entertainment Applications

Mano_._EN.mp4

Mano-P excels not only in enterprise-level business automation but also integrates seamlessly into daily life. This video demonstrates the system's application in Mahjong gameplay: through pure visual understanding of the game interface, it autonomously completes tile recognition, analysis, and decision-making. This case validates Mano-P's general-purpose capabilities beyond work scenarios—from office automation to leisure entertainment, from structured data processing to unstructured game interactions, truly realizing the vision of "AI for Personal." One model, adapting to every aspect of life and work.

Benchmark Performance

Performance of the Mano series models in multiple benchmarks:

1. GUI Grounding

📊 Expand Evaluation Data

2. BUA & CUA

📊 Expand Evaluation Data

OSWorld - Specialized Models

OSWorld - All Models

WebRetriever

3. Perception & Cognition

📊 Expand Evaluation Data

Video-SME-2

Models	Protocol	CA		CV		PAR		Saliency
Models	Protocol	Acc	F1	Acc	F1	Acc	F1	KL↓	CC↑	SIM↑	NSS↑	AUC↑
Random	P1	10.42	11.03	10.76	10.95	15.94	16.00	2.1789	0.0452	0.2852	0.1081	0.5340
Random	P2	10.01	10.74	10.32	10.50	14.39	15.04	4.3378	0.0270	0.2274	0.0665	0.5273
Zero-shot for MLLMs
GPT4o	P1	15.17	6.57	16.11	9.58	16.71	10.34	1.9423	0.4660	0.4602	1.2842	0.7848
GPT4o	P2	10.26	4.77	12.16	7.66	15.00	8.55	2.2650	0.4097	0.4028	1.2418	0.7807
Gemini 2.0 Flash	P1	17.18	5.13	25.06	8.39	24.94	9.52	1.4726	0.3380	0.3751	0.8629	0.7296
Gemini 2.0 Flash	P2	10.45	4.26	12.60	4.95	15.96	7.90	1.6373	0.3542	0.3490	1.0027	0.7590
GPT-5.2	P1	17.83	7.67	22.22	12.55	16.17	9.74	1.3262	0.4852	0.4632	1.3078	0.7969
GPT-5.2	P2	15.31	5.14	19.88	10.27	13.56	7.42	1.5444	0.4379	0.4092	1.3006	0.7999
Claude Sonnet 4.5	P1	10.34	5.8	13.26	9.84	16.02	9.94	1.4235	0.4912	0.4213	1.2956	0.8042
Claude Sonnet 4.5	P2	10.34	5.55	13.27	7.08	16.02	9.6	1.2855	0.4564	0.4781	1.3112	0.7915
Llama 4 Scout	P1	13.98	9.96	10.25	6.51	13.27	8.11	3.7166	0.3331	0.3849	0.8828	0.7238
Llama 4 Scout	P2	10.00	7.33	11.10	8.49	14.35	7.42	3.7434	0.3019	0.3452	0.8848	0.7258
Qwen2.5-VL-7B	P1	15.88	5.21	10.07	6.07	12.26	4.96	12.0586	0.0999	0.2154	0.2578	0.5852
Qwen2.5-VL-7B	P2	10.25	3.95	10.89	5.83	14.39	5.73	12.7596	0.0762	0.1855	0.2195	0.5753
InternVL3-8B	P1	13.35	7.78	14.71	8.02	10.20	6.95	12.6480	0.0572	0.1895	0.1140	0.5769
InternVL3-8B	P2	10.58	6.70	10.94	8.12	12.68	6.32	12.1385	0.0604	0.1819	0.1395	0.5859
Fine-tune for MLLMs
Qwen2.5-VL-7B	P1	22.51	19.11	23.39	10.83	32.06	25.88	1.5091	0.6953	0.6118	1.8937	0.8579
Qwen2.5-VL-7B	P2	13.72	13.25	13.03	10.94	21.24	20.65	2.2496	0.5359	0.4793	1.6439	0.8221
InternVL3-8B	P1	20.94	18.41	21.96	11.02	30.33	24.66	1.2551	0.7014	0.6340	1.9896	0.8670
InternVL3-8B	P2	12.81	11.83	12.16	11.11	19.26	19.27	1.8759	0.6282	0.5467	2.0621	0.8627
Mano-P 1.0
Stage I	P1	31.27	30.53	27.31	25.18	35.16	34.45	0.6794	0.7670	0.7015	2.1347	0.8710
Stage I	P2	21.89	22.06	18.27	18.57	23.77	23.87	1.5759	0.6482	0.6167	2.1021	0.8627
Stage II	P1	32.59	31.46	27.57	25.76	37.73	35.79	0.6736	0.7686	0.7120	2.1688	0.8853
Stage II	P2	20.55	21.26	15.37	15.15	25.36	25.83	0.5617	0.6440	0.6130	2.1090	0.8602
Stage III	P1	34.58	33.99	31.92	28.37	39.42	37.63	0.6073	0.7853	0.7248	2.2103	0.8938
Stage III	P2	25.29	25.83	20.21	19.29	26.49	26.54	1.4617	0.6725	0.6330	2.1788	0.8776

MIT1003 & SalECI

Dataset	Method	Saliency
Dataset	Method	KL↓	CC↑	SIM↑	NSS↑	AUC↑
MIT1003	FastSal	1.036	0.590	0.478	2.008	0.875
	SAM-Resnet	1.247	0.746	0.597	2.752	0.902
	DAV	0.753	0.699	0.566	2.574	0.897
	UNISAL	1.014	0.734	0.597	2.759	0.902
	Transalnet	0.660	0.722	0.592	2.631	0.903
	SUM	0.563	0.768	0.630	2.839	0.913
	Mano-P 1.0	0.648	0.770	0.698	2.950	0.902
SalECI	SSM	0.720	0.599	0.611	1.396	0.830
	DeepGaze IIE	0.995	0.560	0.399	1.327	0.842
	EML-NET	1.220	0.510	0.536	1.232	0.807
	Transalnet	0.873	0.717	0.534	1.723	0.824
	Temp-Sal	0.712	0.719	0.629	1.768	0.813
	SSwinTransformer	0.652	0.687	0.606	1.701	0.868
	Mano-P 1.0	0.615	0.769	0.695	1.735	0.868

ETMD

Saliency Metrics

Methods	Saliency
Methods	CC ↑	SIM ↑	NSS ↑	AUC ↑
ACLNet	0.477	0.329	2.36	0.915
TASED-Net	0.479	0.366	2.63	0.916
STAViS	0.569	0.425	2.94	0.931
ViNet	0.569	0.409	3.06	0.928
CASP-Net	0.620	0.478	3.34	0.940
Mano-P 1.0	0.642	0.481	2.99	0.929

Emotion Recognition

	Emotion Valence		Emotion Arousal
	Acc ↑	Acc ± 1 ↑	Acc ↑	Acc ± 1 ↑
Qwen2.5-VL-7B	13.3	38.1	10.8	35.5
PRISM I	15.8	39.4	12.9	40.4
PRISM II	18.9	43.2	16.6	46.4
Mano-P 1.0	20.2	46.5	18.7	47.3

4. Pruning

📊 Expand Evaluation Data

Online-Mind2Web

Comparison of Task Execution Success Rate (SR) on Online-Mind2Web Benchmark Avg. Tokens/img represents the average visual token retention rate per image; lower values indicate more aggressive pruning.

GSPruning is a novel token pruning method designed for Vision-Language Models to efficiently process high-resolution web interfaces by preserving global spatial structure through anchor points and identifying semantic outliers for critical UI elements. It achieves 2-3× throughput speedup with minimal performance loss, enabling more efficient autonomous web agents.

Model	Method	Avg. Tokens /img ↓	Training samples/s ↑	SR (↑)
Qwen3VL-2B	Baseline (w/o FT)	100%	5.08	0.290
	Baseline (FT)	100%	5.09	0.390
	TextGuide	12.55%	13.54	0.310
	FlashVLM [4]	12.55%	17.01	0.343
	Compressor-VLA [11]	13.33%	16.92	0.293
	HiPrune [16]	25.09%	16.67	0.333
	PDrop [33]	41.47%	10.43	0.330
	IVC	25.09%	7.89	0.303
	Mano-P 1.0	25.09%	20.04	0.370
	Mano-P 1.0	12.57%	22.62	0.336
Qwen3VL-4B	Baseline (FT)	100%	3.24	0.425
	PDrop	41.47%	5.58	0.365
	IVC	25.09%	4.67	0.343
	GSPruning	25.09%	16.72	0.400

5. Context Learning

📊 Expand Evaluation Data

CL Bench

🔧 Skills

Mano-Skill is a desktop GUI automation tool based on the Mano model, driving cross-platform graphical interface operations through natural language. We provide three different usage forms for the same core capability to adapt to different usage scenarios and user groups.

📦 Core Capability Overview

Feature Highlights

Natural Language Driven: Users describe tasks in natural language, and the system automatically executes GUI operations
Flexible Inference Modes:
- Local Mode: Models run locally, data stays on device, fast response
  - Run directly on Mac mini/MacBook (M4 chip or above, 32GB+ RAM)
  - Or use Mano-P computing stick (via USB 4.0 connection)
- Cloud Mode: Without local model configuration, uses cloud API service (mano.mininglamp.com)
- System automatically detects local model configuration and seamlessly switches inference modes
Comprehensive Interaction Support: Click, type, hotkey, scroll, drag, mouse movement, screenshot, wait, app launch, URL navigation
Cross-Platform Support: macOS (stable), Windows, Linux (Beta)

How It Works

Local Mode

Capture current screen screenshot
Run Mano-P model on local device (Mac mini/MacBook) or computing stick for inference
Local model analyzes and returns next action instruction
Client executes operation (click, type, etc.)
Loop execution until task completion

Cloud Mode (Default)

Capture current screen screenshot
Send screenshot and task description to cloud vision model (mano.mininglamp.com)
Cloud model analyzes and returns next action instruction
Local client executes operation (click, type, etc.)
Loop execution until task completion

Data Privacy & Security

Local Mode (Mac mini/MacBook or Computing Stick):

✅ Fully Local Processing: All data processing is completed locally, screenshots and task descriptions never leave the device
✅ Data Stays on Device: Does not access or transmit any data to external servers
✅ Maximum Privacy Protection: Suitable for handling sensitive information and high-security scenarios

Cloud Mode:

⚠️ Data Sent: Screenshots and task descriptions sent to mano.mininglamp.com for real-time visual analysis
✅ Data Not Sent: Does not access or transmit local files, clipboard contents, system credentials
⚠️ Privacy Note: Avoid displaying sensitive documents, chat logs, or credential information on screen when running tasks

General Assurance:

✅ Open Source Auditable: Complete source code publicly available for review

🔧 Three Usage Forms

If you want to use Mano-P directly to accomplish GUI automation tasks, here are three different usage forms. Choose the one that best fits your use case.

1️⃣ mano-cua (CLI Command-Line Tool)

Use Case: Developers, advanced users who need to quickly execute GUI automation tasks in terminal

Installation:

# Install via Homebrew
brew tap HanningWang/tap
brew install mano-cua

The installation process will automatically:

Create an isolated Python 3.13 virtual environment
Install required dependencies (including Tkinter GUI library)
Configure the executable command to system PATH

Usage:

# Run tasks
mano-cua run "Open WeChat and tell FTY the meeting is postponed"
mano-cua run "Search for AI news on Xiaohongshu and display the first post"

# Stop current task
mano-cua stop

Features:

✅ Command-line interface, quick invocation
✅ Virtual environment isolation, no system Python pollution
✅ Suitable for script integration and batch processing
✅ Can be embedded in shell scripts

Project Resources:

Homebrew Tap: github.com/Mininglamp-AI/homebrew-tap

2️⃣ mano-client (Python SDK) ⏳ Planned

Use Case: Python developers who need to integrate GUI automation capabilities into Python projects

Planned Features:

from mano_client import ManoClient

# Create client instance
client = ManoClient()

# Run task
client.run("Open WeChat and tell FTY the meeting is postponed")

# Stop task
client.stop()

Planned Capabilities:

Python API, easy integration into existing Python projects
Supports asynchronous calls and callback functions
Programmable control of task flow
Suitable for building automated workflows

Development Status: Python SDK is under development. Please use CLI tool or Skill form for now.

3️⃣ mano-skill (ClawHub Skill Form)

Use Case: AI agents like Claude Code, OpenClaw that need to autonomously invoke GUI automation capabilities to complete user tasks

Installation:

Option 1: Install via Claude Code

In Claude Code, skills exist as "commands". Installation steps:

Download the skill zip package from ClawHub
After extraction, copy files to Claude Code's commands directory
Restart Claude Code or in a new session, the skill will be automatically available

Option 2: Install via ClawHub CLI (Recommended)

Use the ClawHub CLI tool for one-click installation and skill management:

# Install skill
clawhub install mano-cua

# Install specific version
clawhub install mano-cua --version 1.0.0

# Update skill to latest version
clawhub update mano-cua

After installation, start a new Claude Code or OpenClaw session to use.

Prerequisites: ClawHub CLI tool must be installed first. See: OpenClaw Documentation - ClawHub

Usage:

When users make requests to AI agents that require GUI operations, the agent will automatically invoke this skill:

User: "Help me open WeChat, find FTY's chat window, and tell him the meeting is postponed to tomorrow"
Agent: [Automatically invokes mano-skill to complete GUI operation]

Features:

✅ Autonomously invoked by AI agents, no manual command execution needed
✅ Deeply integrated with agent reasoning capabilities
✅ Suitable for complex multi-step task automation
✅ ClawHub ecosystem with version management and security scanning

Project Resources:

Source Code: github.com/Mininglamp-AI/mano-skill
ClawHub Home: clawhub.ai/HanningWang/mano-cua
Version: v1.0.0
License: MIT

⚙️ Permission Requirements (Common to All Forms)

Screen Recording Permission
Accessibility Permission (keyboard/mouse control)
Grant permissions in System Preferences → Privacy & Security

🔒 Security Constraints (Common to All Forms)

Sensitive or potentially dangerous operations require user confirmation before execution
Users can stop tasks at any time
Only one task can run on each device simultaneously
Only supports primary display (multi-display environment)

📊 Status Panel

When a task is running, a small status panel appears in the top-right corner of the screen to:

Display real-time task status and progress
Provide task management functions (pause/stop)
Remind users that an automation task is running to avoid accidental interference

🔔 Platform Compatibility Note

Beta Version Notice: Mano-Skill is currently in Beta testing phase.

macOS: ✅ Preferred and most thoroughly tested platform, stable and ready for use
Windows and Linux: ⚠️ Platform adaptations not yet fully completed, minor issues may occur

We are continuously improving cross-platform compatibility. Feedback is welcome.

Models

If you want to integrate Mano-P's model capabilities into your own applications, this section provides performance metrics and usage guidelines. Models will be released soon.

Performance Evaluation

Our Mano-P model, after pruning with our proprietary GS-Pruning algorithm, achieves real-time performance on 4K-context tasks on the Apple M4 Pro chip. The relevant models and methods will be released soon. The table below presents the actual benchmark results on the M4 Pro.

Model	Chip	Bandwidth	Framework	Context Length	Pruning Rate	Prefill Speed (tokens/s)	Decode Speed (tokens/s)	Peak Memory (GB)	Prefill Time (s)	Decode Time (s)
Mano-P 1.0-4B (w4a16)	Apple M4 Pro 64GB RAM	273 GB/s	Mano-SDK	4112	0.5	476.952	76.75	4.356	8.621	0.265
Mano-P 1.0-4B (w4a16)	Apple M4 Pro 64GB RAM	273 GB/s	Mano-SDK	8208	0.5	331.0	70.946	5.1471	24.792	0.253

Model will be released soon

Approach

If you are a researcher or wish to train customized GUI Agent models based on your own data, we plan to open-source the complete Mano-Action training methodology and related tools.

Release Soon

Mano-Action Training Methodology

Mano-Action is a bidirectional self-reinforcement training framework specifically designed for GUI Grounding. Unlike traditional unidirectional prediction methods, Mano-Action achieves more robust interface understanding through Text↔Action cycle consistency learning, enabling the model to master both "locating elements from descriptions" and "describing given elements" simultaneously.

Core Features

Bidirectional Cycle Learning: Mutual reinforcement between Text → Action and Action → Text
Three-Stage Progressive Training: Supervised Learning → Offline RL → Online RL
Closed-Loop Data Generation: Automatically generate high-quality training data for continuous model improvement
Edge Optimization Adaptation: Includes quantization, pruning, and other edge deployment optimization techniques

Use Cases

🎓 Academic Research: Explore new approaches to GUI understanding and multimodal interaction
🏢 Enterprise Customization: Train specialized models based on internal enterprise systems
🌐 Domain Adaptation: Fine-tune models for specific domains (healthcare, finance, etc.)
🔬 Algorithm Innovation: Develop new training techniques building on Mano-Action

🌟 Technical Advantages

Mano-P vs Traditional Solutions CUA Comparison

Feature	Mano-P	OpenClaw	Manus	Traditional RPA
Model Source	✅ Built-in edge model	⚠️ User-configured	⚠️ Cloud API calls	❌ No model (rule-based engine)
Data Security	✅ Local execution	⚠️ LLM/skill cloud calls	⚠️ Cloud inference	✅ Can be local
Control Method	✅ Pure visual	⚠️ CDP protocol+CLI	❌ HTML parsing+CLI	❌ System API
Use Scenarios	✅ All-platform GUI	✅ Cross-platform apps	⚠️ Web apps only	⚠️ Specific systems
Long Task Plan	✅ Autonomous planning	✅ Autonomous planning	✅ Visual flow orchestration	❌ Needs preset workflows
Response Speed	✅ Instant response	✅ Local/cloud execution	⚠️ Cloud latency	✅ Instant response
Deployment Cost	✅ Low-cost entry	✅ Open source & free	⚠️ Subscription fee	✅ Low cost
Robustness	✅ UI change adaptive	✅ LLM adaptive	⚠️ Limited adaptation	❌ UI change needs reconfig

Core Competitiveness

Edge Large Model + Flexible Deployment
- 4B model runs directly on Mac (M4 chip + 32GB RAM)
- Large parameter models (72B) supported via computing stick
- No API key configuration needed, ready out-of-the-box
- Significant advantage over OpenClaw (requires user model configuration) and Manus (cloud calls)
Universal Visual Understanding
- Pure visual GUI interaction, not limited to browsers and web apps
- Broader support than OpenClaw (CDP protocol mainly for browsers) and Manus (web apps only)
- Supports desktop software, 3D applications, professional tools, and non-standard GUIs
Offline Long-Task Autonomous Planning
- Fully offline reasoning for complex business processes
- Autonomous decision-making and error correction without internet connection
- Unique advantage over Manus (cloud latency) and traditional RPA (needs preset workflows)
Integrated Hardware Deployment
- Model + computing stick integrated solution, plug-and-play
- Lowers technical barrier compared to OpenClaw (open-source & free but requires self-deployment)
- Cross-platform compatible, rapid deployment and launch

📄 Technical Papers & Citation

Related Papers

Mano-P is based on the following research work:

1. Mano Series Model Foundation Paper

@article{mano-2025,
  title={Mano Technical Report},
  author={Tianyu Fu, Anyang Su, Chenxu Zhao, Hanning Wang, Minghui Wu, Zhe Yu, Fei Hu, Mingjia Shi, Wei Dong, Jiayao Wang, Yuyang Chen, Ruiyang Yu, Siran Peng, Menglin Li, Nan Huang, Haitian Wei, Jiawei Yu, Yi Xin, Xilin Zhao, Kai Gu, Ping Jiang, Sifan Zhou, Shuo Wang},
  journal={arXiv preprint arXiv:2509.17336},
  year={2025},
  url={https://arxiv.org/abs/2509.17336}
}

2. WebRetriever Benchmark

@article{webretriever-2026,
  title={WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation},
  author={Wei Dong and Tianyu Fu and Zhe Yu and Hanning Wang and Anyang Su and Zhizhou Fang and Yuyang Chen and Shuo Wang and Minghui Wu and Ping Jiang and Zhen Lei and Chenxu Zhao},
  year={2026},
  note={To be published},
  url={https://github.com/hhhhhhalf/WebRetriever}
}

Academic Collaboration

We welcome collaboration with academia:

🔬 Dataset Contribution: Provide new GUI task datasets
🤝 Joint Research: Collaborate on edge deployment, quantization optimization, GUI understanding, etc.
📚 Benchmarking: Test Mano-P on new evaluation sets

For academic collaboration inquiries, please contact: model@mininglamp.com

❓ FAQ

🤖 What is Mano-P?

Mano-P is an open-source GUI-VLA (Vision-Language-Action) agent designed to run locally on Apple Silicon edge devices. It uses pure visual understanding to automate desktop GUI operations across platforms.

⚖️ How does Mano-P compare to Claude Computer Use?

Performance Comparison:

OSWorld (all models): Claude Sonnet 4.6 72.1% vs Mano-P 1.0-72B 58.2%
WebRetriever Protocol I: Mano-P 41.7 NavEval vs Claude 4.5 Computer Use 31.3

Key Difference:

✅ Mano-P runs entirely on-device, no data leaves the machine
⚠️ Claude Computer Use requires cloud API calls

Use Case: Mano-P is particularly suitable for high-security scenarios.

🔌 Can Mano-P run without internet?

Yes! In local mode, all model inference runs on the Apple M4 device. ✅ No screenshots or task descriptions are sent to external servers.

💻 What hardware do I need?

Minimum Requirements:

Mac mini or MacBook
Apple M4 chip
32GB RAM

Alternative:

Any Mac + Mano-P computing stick (connected via USB 4.0+)

📌 We plan to support more devices in the future.

📦 How do I install Mano-P?

CLI Tool:

brew tap HanningWang/tap && brew install mano-cua

OpenClaw/Claude Code Skill: See ClawHub - Mano-CUA

🔒 Is my data safe?

Local Mode: ✅ All processing happens on-device

Cloud Mode:

⚠️ Only screenshots and task descriptions sent to mano.mininglamp.com
✅ No local files, clipboard contents, or credentials accessed

Transparency: Full client is open-source for audit

🤝 Contribution Guidelines

We welcome community contributions! If you want to contribute to the project:

Fork this repository
Create your feature branch (git checkout -b feature/AmazingFeature)
Commit your changes (git commit -m 'Add some AmazingFeature')
Push to the branch (git push origin feature/AmazingFeature)
Open a Pull Request

Contribution Areas

🐛 Bug fixes and issue reporting
📝 Documentation improvements and translations
💡 New feature suggestions and implementations
🧪 Test cases and benchmarking
🎨 Application scenarios and demo contributions

📄 License

This project is licensed under the Apache License 2.0.

License Highlights:

✅ Commercial use
✅ Modification and distribution
✅ Patent grant
⚠️ Must retain copyright notice
⚠️ Must state changes

📮 Contact

📧 Email: model@mininglamp.com
🏠 Website: https://github.com/Mininglamp-AI/Mano-P
💬 Community: (To be added)
🐛 GitHub Issues: https://github.com/Mininglamp-AI/Mano-P/issues

🙏 Acknowledgments

Thanks to all developers and researchers who contributed to this project.

Special Thanks:

Mano project team for providing the technical foundation
DeepMiner platform for deep integration support
Edge computing hardware partners
Open source community contributors

_{Built with ❤️ by the Mano-P Team}

Name		Name	Last commit message	Last commit date
Latest commit History 20 Commits
pics		pics
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
README_CN.md		README_CN.md

Folders and files

Latest commit

History

Repository files navigation

Mano-P 1.0

Overview

Main Capabilities

Technical Background

🎯 Key Highlights

🎬 Use Case Demonstrations

Scenario 1: Mano-afk Fully automated application construction

Scenario 2: Commercial video intelligent system

Scenario 3: Local model task execution

Scenario 4: Daily Life and Entertainment Applications

Benchmark Performance

1. GUI Grounding

2. BUA & CUA

OSWorld - Specialized Models

OSWorld - All Models

WebRetriever

3. Perception & Cognition

Video-SME-2

MIT1003 & SalECI

ETMD

Saliency Metrics

Emotion Recognition

4. Pruning

Online-Mind2Web

5. Context Learning

CL Bench

🔧 Skills

📦 Core Capability Overview

Feature Highlights

How It Works

Data Privacy & Security

🔧 Three Usage Forms

1️⃣ mano-cua (CLI Command-Line Tool)

2️⃣ mano-client (Python SDK) ⏳ Planned

3️⃣ mano-skill (ClawHub Skill Form)

⚙️ Permission Requirements (Common to All Forms)

🔒 Security Constraints (Common to All Forms)

📊 Status Panel

🔔 Platform Compatibility Note

Models

Performance Evaluation

Approach

Mano-Action Training Methodology

Core Features

Use Cases

🌟 Technical Advantages

Mano-P vs Traditional Solutions CUA Comparison

Core Competitiveness

📄 Technical Papers & Citation

Related Papers

Academic Collaboration

❓ FAQ

🤝 Contribution Guidelines

Contribution Areas

📄 License

📮 Contact

🙏 Acknowledgments

About

Topics

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Uh oh!

Contributors

Uh oh!

Packages