|
1 |
| -# Browser Operator [Chromium DevTools with Agentic Framework] |
| 1 | +# Browser Operator - Open Source Agentic Browser |
2 | 2 |
|
3 |
| -Chromium browser with an user interface to run multi-agent workflows directly on the browser using a stateful, orchestration framework. |
| 3 | + |
| 4 | + |
| 5 | +[](LICENSE) |
4 | 6 |
|
| 7 | +**The first open-source, privacy-friendly AI browser that transforms how you work on the web. Your intelligent partner for research, analysis, and automation - all running locally in your browser.** |
5 | 8 |
|
6 | 9 | 
|
7 | 10 |
|
| 11 | +## 🚀 Download & Get Started |
8 | 12 |
|
9 |
| -## Quick Start |
| 13 | +**[⬇️ Download Browser Operator for macOS](https://github.com/tysonthomas9/browser-operator-devtools-frontend/releases)** |
10 | 14 |
|
11 |
| -[Download the Agentic Browser for MacOS](https://github.com/tysonthomas9/browser-operator-devtools-frontend/releases) |
| 15 | +Or build from source: [Developer Setup Guide](front_end/panels/ai_chat/Readme.md) |
12 | 16 |
|
13 |
| -Or |
| 17 | +## 🎬 See It In Action |
14 | 18 |
|
15 |
| -[Set up the chromium dev tools with Agent framework on your system](front_end/panels/ai_chat/Readme.md) |
| 19 | +### Deep Research & Analysis |
| 20 | +Watch Browser Operator synthesize information from multiple sources, creating comprehensive research reports without manual copying and pasting. |
16 | 21 |
|
17 |
| -Note: Read this document to know more about the [build](front_end/panels/ai_chat/docs/PreBuilt.md) |
18 | 22 |
|
19 |
| -## Key Capabilities |
| 23 | +https://github.com/user-attachments/assets/225319db-c5a0-4834-9f37-5787fb646d16 |
20 | 24 |
|
21 |
| -* Built in Agent Framework for running tasks / workflows. |
22 |
| -* Ability to perform actions such as: Navigate URLs, Perform Actions (Clicks, Fill Form, Scroll). |
23 |
| -* The agent can autonmously plan and execute tasks on behalf of user, such as |
24 |
| - * Summarize content |
25 |
| - * Deep research topics |
26 |
| - * Literature reviews |
27 |
| - * Product comparisons |
28 |
| - * Shopping assistance |
29 |
| - * Advanced search |
30 |
| - * And many more |
31 |
| -* Integrates with 100+ LLM Models |
32 |
| - * OpenAI GPT-4.1, O4-Mini |
33 |
| - * Claude 4, 3.7, 3.5 |
34 |
| - * Google Gemeni |
35 |
| - * Llama |
36 |
| - * Deepseek |
37 |
| - * Qwen |
38 |
| - * And many more |
39 |
| -* Integrates with LiteLLM which supports ability to use multiple providers |
40 |
| - * Huggingface |
41 |
| - * Groq |
42 |
| - * Azure |
43 |
| - * AWS |
44 |
| - * OpenRouter |
45 |
| - * vLLM |
46 |
| - * Ollama |
47 |
| - * And many more |
48 |
| -* Customize workflows or agent behavior with config changes. |
49 | 25 |
|
50 |
| - |
| 26 | +### Smart Shopping Assistant |
| 27 | +See how it automatically compares products, analyzes reviews, and helps you make informed purchasing decisions. |
51 | 28 |
|
52 |
| -## Demos |
| 29 | +https://github.com/user-attachments/assets/c478b18e-0342-400d-98ab-222c93eecd7a |
53 | 30 |
|
54 |
| -Watch Browser Operator in action with our demo videos: |
| 31 | +### Professional Research |
| 32 | +Discover how businesses use Browser Operator for talent search, competitive analysis, and market research. |
55 | 33 |
|
56 |
| -#### Deep Research |
57 |
| -Browser Operator seamlessly integrates public web data with your private documents and knowledge bases, creating comprehensive research without switching between tools. |
| 34 | +https://github.com/user-attachments/assets/90150f0e-e8c8-4b53-b6a6-c739f143f4a0 |
58 | 35 |
|
59 |
| -https://github.com/user-attachments/assets/225319db-c5a0-4834-9f37-5787fb646d16 |
| 36 | +## ✨ Key Features |
| 37 | + |
| 38 | +### 🤖 Intelligent Automation |
| 39 | +- **Multi-Agent Framework**: Specialized agents work together to handle complex tasks |
| 40 | +- **Autonomous Navigation**: Understands and interacts with any website |
| 41 | +- **Smart Actions**: Click, fill forms, extract data, and navigate without manual scripting |
| 42 | +- **Adaptive Learning**: Improves task execution based on patterns and feedback |
| 43 | + |
| 44 | +### 🔒 Privacy First (Use local LLM) |
| 45 | +- **Local Processing**: Your data never leaves your machine |
| 46 | +- **No Cloud Dependencies**: Full functionality without sending data to external servers |
| 47 | +- **Secure Sessions**: Works with your existing browser authentication |
| 48 | +- **Open Source**: Complete transparency in how your data is handled |
60 | 49 |
|
61 |
| -#### Product Discovery & Comparison |
62 |
| -Streamline your shopping research by automatically gathering specifications, user ratings, and availability across retailers, to help you make confident purchasing decisions. |
| 50 | +### 🧩 Extensible Platform |
| 51 | +- **100+ AI Models**: Support for OpenAI, Claude, Gemini, Llama, and more |
| 52 | +- **Custom Workflows**: Build your own automation sequences |
| 53 | +- **Plugin Architecture**: Extend functionality with custom agents |
| 54 | +- **API Integration**: Connect with your existing tools and services |
63 | 55 |
|
64 |
| -https://github.com/user-attachments/assets/c478b18e-0342-400d-98ab-222c93eecd7a |
| 56 | +## 💡 What Can You Build? |
65 | 57 |
|
66 |
| -#### Professional Talent Search |
67 |
| -Efficiently discover and evaluate potential candidates based on skills, experience, and portfolio quality, creating detailed profiles for recruitment decision-making. |
| 58 | +<table> |
| 59 | +<tr> |
| 60 | +<td width="50%"> |
68 | 61 |
|
69 |
| -https://github.com/user-attachments/assets/90150f0e-e8c8-4b53-b6a6-c739f143f4a0 |
| 62 | +**Personal Productivity** |
| 63 | +- 📚 Literature reviews and research papers |
| 64 | +- 🛍️ Price tracking and comparison shopping |
| 65 | +- 📰 News aggregation and summarization |
| 66 | +- 📊 Data collection and analysis |
| 67 | +- ✈️ Travel planning and booking research |
| 68 | + |
| 69 | +</td> |
| 70 | +<td width="50%"> |
| 71 | + |
| 72 | +**Business Intelligence** |
| 73 | +- 🔍 Competitive analysis and monitoring |
| 74 | +- 👥 Talent sourcing and recruitment |
| 75 | +- 📈 Market research and trends |
| 76 | +- 🏢 Lead generation and qualification |
| 77 | +- 📋 Compliance and audit automation |
| 78 | + |
| 79 | +</td> |
| 80 | +</tr> |
| 81 | +</table> |
| 82 | + |
| 83 | +## 🛠️ Technical Architecture |
| 84 | + |
| 85 | +Browser Operator combines a Chromium-based browser with an advanced agentic framework: |
| 86 | + |
| 87 | +``` |
| 88 | +┌─────────────────────────────────────────────────┐ |
| 89 | +│ Browser Operator UI │ |
| 90 | +├─────────────────────────────────────────────────┤ |
| 91 | +│ Multi-Agent Orchestrator │ |
| 92 | +├──────────────┬────────────────┬─────────────────┤ |
| 93 | +│ Research │ Navigation │ Analysis │ |
| 94 | +│ Agent │ Agent │ Agent │ |
| 95 | +├──────────────┴────────────────┴─────────────────┤ |
| 96 | +│ Chromium Browser Engine │ |
| 97 | +└─────────────────────────────────────────────────┘ |
| 98 | +``` |
| 99 | + |
| 100 | +### Core Components |
| 101 | +- **Orchestrator Agent**: Coordinates multi-agent workflows and task distribution |
| 102 | +- **Navigation Engine**: Handles web interactions and page understanding |
| 103 | +- **Tool Registry**: Extensible system for adding new capabilities |
| 104 | +- **State Management**: Maintains context across complex workflows |
| 105 | + |
| 106 | +[Full Technical Documentation →](front_end/panels/ai_chat/Readme.md) |
| 107 | + |
| 108 | +## ⚙️ Quick Setup |
| 109 | + |
| 110 | +### For Users: Pre-built Application |
| 111 | + |
| 112 | +1. [Download the latest release](https://github.com/tysonthomas9/browser-operator-devtools-frontend/releases) |
| 113 | +2. Open Browser Operator |
| 114 | +3. Configure your AI provider (see below) |
| 115 | +4. Start automating! |
| 116 | + |
| 117 | +### For Developers: Build from Source |
| 118 | + |
| 119 | +```bash |
| 120 | +# Clone the repository |
| 121 | +git clone https://github.com/tysonthomas9/browser-operator-devtools-frontend.git |
| 122 | + |
| 123 | +# Follow the detailed build instructions |
| 124 | +cd browser-operator-devtools-frontend |
| 125 | +# See front_end/panels/ai_chat/Readme.md for complete setup |
| 126 | +``` |
70 | 127 |
|
71 |
| -### Quick Roadmap |
| 128 | +### AI Provider Configuration |
72 | 129 |
|
73 |
| -|Features| Status | |
74 |
| -|--|--| |
75 |
| -| Multi-Agent Workflow | Completed (Initial Release) | |
76 |
| -| OpenAI LLM | Completed (Initial Release) | |
77 |
| -| Local LLM | Completed (May 22) | |
78 |
| -| MCP | Planned | |
79 |
| -| Customize System Prompts in UI| Planned | |
80 |
| -| Customize Agents in UI| Planned | |
81 |
| -| Customize Workflow Graphs in UI| Planned | |
82 |
| -| Eval Management | Planned | |
83 |
| -| Memory | Planned | |
84 |
| -| A2A Protocol | Planned | |
| 130 | +<details> |
| 131 | +<summary><b>Option 1: OpenAI (Recommended for beginners)</b></summary> |
85 | 132 |
|
86 |
| -### DevTools Documentation |
| 133 | +1. Get an API key from [OpenAI Platform](https://platform.openai.com) |
| 134 | +2. Open Browser Operator settings |
| 135 | +3. Select "OpenAI" as provider |
| 136 | +4. Enter your API key |
| 137 | +5. Choose a model (GPT-4.1 recommended) |
| 138 | +6. Save and start using! |
87 | 139 |
|
88 |
| -- [Agentic Framework Documentation](front_end/panels/ai_chat/Readme.md) |
89 |
| -- [Chromium Devtools Original Documentation](https://chromium.googlesource.com/devtools/devtools-frontend/+/main/docs/README.md) |
| 140 | +</details> |
90 | 141 |
|
91 |
| -### Agentic Framework Documentation |
| 142 | +<details> |
| 143 | +<summary><b>Option 2: LiteLLM (For multiple providers)</b></summary> |
92 | 144 |
|
93 |
| -* [`front_end/panels/ai_chat/core/Readme.md`](front_end/panels/ai_chat/core/Readme.md): Explains how to customize the `BaseOrchestratorAgent` to add new top-level agent types and UI buttons, and details its graph-based workflow. |
94 |
| -* [`front_end/panels/ai_chat/agent_framework/Readme.md`](front_end/panels/ai_chat/agent_framework/Readme.md): Describes the AI Agent Framework, its core components (`ConfigurableAgentTool`, `AgentRunner`, `ToolRegistry`), and how to create, configure, and register new custom agents, including agent handoff mechanisms. |
| 145 | +Perfect for using multiple AI providers or self-hosted models: |
95 | 146 |
|
96 |
| -### Setup LiteLLM Configuration |
| 147 | +1. Set up your LiteLLM proxy server |
| 148 | +2. Select "LiteLLM Provider" in settings |
| 149 | +3. Enter proxy URL and API key |
| 150 | +4. Click "Fetch Models" to verify connection |
| 151 | +5. Select your preferred model |
97 | 152 |
|
98 |
| -https://github.com/user-attachments/assets/579dcfdc-71c8-4664-87b8-c2b68cc5c1ce |
| 153 | +[LiteLLM Setup Video →](https://github.com/user-attachments/assets/579dcfdc-71c8-4664-87b8-c2b68cc5c1ce) |
99 | 154 |
|
100 |
| -1. Click on the setting config inside the chat panel |
101 |
| -2. Select LiteLLM Provider |
102 |
| -3. Input the LiteLLM URL and API key |
103 |
| -4. Click on fetch models to test the configuration |
104 |
| -5. Click save to update the configuration |
| 155 | +</details> |
| 156 | + |
| 157 | +<details> |
| 158 | +<summary><b>Option 3: Local Models (Maximum privacy)</b></summary> |
| 159 | + |
| 160 | +Run completely offline with Ollama: |
| 161 | + |
| 162 | +1. Install Ollama on your system |
| 163 | +2. Pull your preferred model (e.g., `ollama pull llama3`) |
| 164 | +3. Configure Browser Operator to use local endpoint |
| 165 | +4. Enjoy private, offline automation |
| 166 | + |
| 167 | +</details> |
| 168 | + |
| 169 | +## 🗺️ Roadmap |
| 170 | + |
| 171 | +### ✅ Released |
| 172 | +- Multi-agent workflow engine |
| 173 | +- Support for 100+ AI models |
| 174 | +- macOS application |
| 175 | +- Core automation capabilities |
| 176 | + |
| 177 | +### 🚧 In Development |
| 178 | +- Windows and Linux support |
| 179 | +- Enhanced memory system |
| 180 | +- Custom agent builder |
| 181 | + |
| 182 | +### 🔮 Planned Features |
| 183 | +- MCP (Model Context Protocol) support |
| 184 | +- Visual workflow designer |
| 185 | +- Team collaboration features |
| 186 | +- Advanced scheduling system |
| 187 | + |
| 188 | +## 👥 Community & Support |
| 189 | + |
| 190 | +### Get Help |
| 191 | +- 📖 [Documentation](front_end/panels/ai_chat/Readme.md) |
| 192 | +- 💬 [Discord Community](https://discord.gg/fp7ryHYBSY) |
| 193 | +- 🐛 [Report Issues](https://github.com/tysonthomas9/browser-operator-devtools-frontend/issues) |
| 194 | +- 🐦 [Follow Updates](https://x.com/BrowserOperator) |
105 | 195 |
|
106 | 196 | ### Contributing
|
107 | 197 |
|
108 |
| -Found a bug 🐛 or have a feature idea ✨? Please create issues [here](https://github.com/tysonthomas9/browser-operator-devtools-frontend/issues) |
| 198 | +We welcome contributions! Here's how you can help: |
| 199 | + |
| 200 | +- **🐛 Report Bugs**: Help us identify and fix issues |
| 201 | +- **✨ Request Features**: Share your ideas for new capabilities |
| 202 | +- **📝 Improve Docs**: Help others get started |
| 203 | +- **💻 Submit PRs**: Contribute code improvements |
| 204 | + |
| 205 | +See our [Contributing Guide](CONTRIBUTING.md) for details. |
| 206 | + |
| 207 | +## 📚 Documentation |
| 208 | + |
| 209 | +- [Getting Started Guide](front_end/panels/ai_chat/docs/GettingStarted.md) |
| 210 | +- [Agent Framework](front_end/panels/ai_chat/agent_framework/Readme.md) |
| 211 | +- [Creating Custom Agents](front_end/panels/ai_chat/core/Readme.md) |
| 212 | +- [Architecture Overview](front_end/panels/ai_chat/docs/Architecture.md) |
| 213 | +- [Build Instructions](front_end/panels/ai_chat/docs/PreBuilt.md) |
| 214 | + |
| 215 | +## 🙏 Acknowledgments |
| 216 | + |
| 217 | +Browser Operator is built on top of Chromium and integrates with numerous open-source projects. Special thanks to all contributors and the open-source community. |
| 218 | + |
| 219 | +## 📄 License |
| 220 | + |
| 221 | +Browser Operator is released under the [BSD-3-Clause License](LICENSE). |
| 222 | + |
| 223 | +--- |
109 | 224 |
|
110 |
| -### Join Us |
| 225 | +<div align="center"> |
111 | 226 |
|
112 |
| -If you like this project, don't hesitate to ⭐ star this repository. For those who'd like to contribute code or just hang out with the community please join our Discord. |
| 227 | +**⭐ Star this repo to support open-source AI development!** |
113 | 228 |
|
114 |
| -[](https://discord.gg/JKYuuubr) |
115 |
| -[-000000?style=for-the-badge&logo=x&logoColor=white)](https://x.com/BrowserOperator) |
| 229 | +</div> |
0 commit comments