Google Gemini on Producthunt daily

bytebot

Sat, 06 Sep 2025 15:23:40 +0800

bytebot-ai/bytebot

Bytebot: Open-Source AI Desktop Agent

An AI that has its own computer to complete tasks for you

🌐 Website • 📚 Documentation • 💬 Discord • 𝕏 Twitter

https://github.com/user-attachments/assets/f271282a-27a3-43f3-9b99-b34007fdd169

https://github.com/user-attachments/assets/72a43cf2-bd87-44c5-a582-e7cbe176f37f

What is a Desktop Agent?

A desktop agent is an AI that has its own computer. Unlike browser-only agents or traditional RPA tools, Bytebot comes with a full virtual desktop where it can:

Use any application (browsers, email clients, office tools, IDEs)
Download and organize files with its own file system
Log into websites and applications using password managers
Read and process documents, PDFs, and spreadsheets
Complete complex multi-step workflows across different programs

Think of it as a virtual employee with their own computer who can see the screen, move the mouse, type on the keyboard, and complete tasks just like a human would.

Why Give AI Its Own Computer?

When AI has access to a complete desktop environment, it unlocks capabilities that aren’t possible with browser-only agents or API integrations:

Complete Task Autonomy

Give Bytebot a task like “Download all invoices from our vendor portals and organize them into a folder” and it will:

Open the browser
Navigate to each portal
Handle authentication (including 2FA via password managers)
Download the files to its local file system
Organize them into a folder

Process Documents

Upload files directly to Bytebot’s desktop and it can:

Read entire PDFs into its context
Extract data from complex documents
Cross-reference information across multiple files
Create new documents based on analysis
Handle formats that APIs can’t access

Use Real Applications

Bytebot isn’t limited to web interfaces. It can:

Use desktop applications like text editors, VS Code, or email clients
Run scripts and command-line tools
Install new software as needed
Configure applications for specific workflows

Quick Start

Deploy in 2 Minutes

Option 1: Railway (Easiest)

Just click and add your AI provider API key.

Option 2: Docker Compose

git clone https://github.com/bytebot-ai/bytebot.git
cd bytebot

# Add your AI provider key (choose one)
echo "ANTHROPIC_API_KEY=sk-ant-..." > docker/.env
# Or: echo "OPENAI_API_KEY=sk-..." > docker/.env
# Or: echo "GEMINI_API_KEY=..." > docker/.env

docker-compose -f docker/docker-compose.yml up -d

# Open http://localhost:9992

Full deployment guide →

How It Works

Bytebot consists of four integrated components:

Virtual Desktop: A complete Ubuntu Linux environment with pre-installed applications
AI Agent: Understands your tasks and controls the desktop to complete them
Task Interface: Web UI where you create tasks and watch Bytebot work
APIs: REST endpoints for programmatic task creation and desktop control

Key Features

Natural Language Tasks: Just describe what you need done
File Uploads: Drop files onto tasks for Bytebot to process
Live Desktop View: Watch Bytebot work in real-time
Takeover Mode: Take control when you need to help or configure something
Password Manager Support: Install 1Password, Bitwarden, etc. for automatic authentication
Persistent Environment: Install programs and they stay available for future tasks

Example Tasks

Basic Examples

1
2
3

"Go to Wikipedia and create a summary of quantum computing"
"Research flights from NYC to London and create a comparison document"
"Take screenshots of the top 5 news websites"

Document Processing

1
2
3

"Read the uploaded contracts.pdf and extract all payment terms and deadlines"
"Process these 5 invoice PDFs and create a summary report"
"Download and analyze the latest financial report and answer: What were the key risks mentioned?"

Multi-Application Workflows

1
2
3

"Download last month's bank statements from our three banks and consolidate them"
"Check all our vendor portals for new invoices and create a summary report"
"Log into our CRM, export the customer list, and update records in the ERP system"

Programmatic Control

Create Tasks via API

import requests

# Simple task
response = requests.post('http://localhost:9991/tasks', json={
    'description': 'Download the latest sales report and create a summary'
})

# Task with file upload
files = {'files': open('contracts.pdf', 'rb')}
response = requests.post('http://localhost:9991/tasks',
    data={'description': 'Review these contracts for important dates'},
    files=files
)

Direct Desktop Control

# Take a screenshot
curl -X POST http://localhost:9990/computer-use \
  -H "Content-Type: application/json" \
  -d '{"action": "screenshot"}'

# Click at specific coordinates
curl -X POST http://localhost:9990/computer-use \
  -H "Content-Type: application/json" \
  -d '{"action": "click_mouse", "coordinate": [500, 300]}'

Full API documentation →

Setting Up Your Desktop Agent

1. Deploy Bytebot

Use one of the deployment methods above to get Bytebot running.

2. Configure the Desktop

Use the Desktop tab in the UI to:

Install additional programs you need
Set up password managers for authentication
Configure applications with your preferences
Log into websites you want Bytebot to access

3. Start Giving Tasks

Create tasks in natural language and watch Bytebot complete them using the configured desktop.

Use Cases

Business Process Automation

Invoice processing and data extraction
Multi-system data synchronization
Report generation from multiple sources
Compliance checking across platforms

Development & Testing

Automated UI testing
Cross-browser compatibility checks
Documentation generation with screenshots
Code deployment verification

Research & Analysis

Competitive analysis across websites
Data gathering from multiple sources
Document analysis and summarization
Market research compilation

Architecture

Bytebot is built with:

Desktop: Ubuntu 22.04 with XFCE, Firefox, VS Code, and other tools
Agent: NestJS service that coordinates AI and desktop actions
UI: Next.js application for task management
AI Support: Works with Anthropic Claude, OpenAI GPT, Google Gemini
Deployment: Docker containers for easy self-hosting

Why Self-Host?

Data Privacy: Everything runs on your infrastructure
Full Control: Customize the desktop environment as needed
No Limits: Use your own AI API keys without platform restrictions
Flexibility: Install any software, access any systems

Advanced Features

Multiple AI Providers

Use any AI provider through our LiteLLM integration:

Azure OpenAI
AWS Bedrock
Local models via Ollama
100+ other providers

Enterprise Deployment

Deploy on Kubernetes with Helm:

# Clone the repository
git clone https://github.com/bytebot-ai/bytebot.git
cd bytebot

# Install with Helm
helm install bytebot ./helm \
  --set agent.env.ANTHROPIC_API_KEY=sk-ant-...

Enterprise deployment guide →

Community & Support

Discord: Join our community for help and discussions
Documentation: Comprehensive guides at docs.bytebot.ai
GitHub Issues: Report bugs and request features

Contributing

We welcome contributions! Whether it’s:

🐛 Bug fixes
✨ New features
📚 Documentation improvements
🌐 Translations

Please:

Check existing issues first
Open an issue to discuss major changes
Submit PRs with clear descriptions
Join our Discord to discuss ideas

License

Bytebot is open source under the Apache 2.0 license.

Give your AI its own computer. See what it can do.

_{Built by Tantl Labs and the open source community}

claude-task-master

Tue, 10 Jun 2025 15:29:20 +0800

eyaltoledano/claude-task-master

Task Master

By @eyaltoledano, @RalphEcom & @jasonzhou1993

A task management system for AI-driven development with Claude, designed to work seamlessly with Cursor AI.

Documentation

For more detailed information, check out the documentation in the docs directory:

Configuration Guide - Set up environment variables and customize Task Master
Tutorial - Step-by-step guide to getting started with Task Master
Command Reference - Complete list of all available commands
Task Structure - Understanding the task format and features
Example Interactions - Common Cursor AI interaction examples
Migration Guide - Guide to migrating to the new project structure

Quick Install for Cursor 1.0+ (One-Click)

Note: After clicking the install button, you’ll still need to add your API keys to the configuration. The button installs the MCP server with placeholder keys that you’ll need to replace with your actual API keys.

Requirements

Taskmaster utilizes AI across several commands, and those require a separate API key. You can use a variety of models from different AI providers provided you add your API keys. For example, if you want to use Claude 3.7, you’ll need an Anthropic API key.

You can define 3 types of models to be used: the main model, the research model, and the fallback model (in case either the main or research fail). Whatever model you use, its provider API key must be present in either mcp.json or .env.

At least one (1) of the following is required:

Anthropic API key (Claude API)
OpenAI API key
Google Gemini API key
Perplexity API key (for research model)
xAI API Key (for research or main model)
OpenRouter API Key (for research or main model)

Using the research model is optional but highly recommended. You will need at least ONE API key. Adding all API keys enables you to seamlessly switch between model providers at will.

Quick Start

Option 1: MCP (Recommended)

MCP (Model Control Protocol) lets you run Task Master directly from your editor.

1. Add your MCP config at the following path depending on your editor

Editor	Scope	Linux/macOS Path	Windows Path	Key
Cursor	Global	`~/.cursor/mcp.json`	`%USERPROFILE%\.cursor\mcp.json`	`mcpServers`
	Project	`<project_folder>/.cursor/mcp.json`	`<project_folder>\.cursor\mcp.json`	`mcpServers`
Windsurf	Global	`~/.codeium/windsurf/mcp_config.json`	`%USERPROFILE%\.codeium\windsurf\mcp_config.json`	`mcpServers`
VS Code	Project	`<project_folder>/.vscode/mcp.json`	`<project_folder>\.vscode\mcp.json`	`servers`

Manual Configuration

Cursor & Windsurf (`mcpServers`)

{
  "mcpServers": {
    "taskmaster-ai": {
      "command": "npx",
      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
      "env": {
        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
        "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
        "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
        "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
        "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
        "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
        "OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
      }
    }
  }
}

🔑 Replace YOUR_…_KEY_HERE with your real API keys. You can remove keys you don’t use.

VS Code (`servers` + `type`)

{
  "servers": {
    "taskmaster-ai": {
      "command": "npx",
      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
      "env": {
        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
        "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
        "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
        "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
        "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
        "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE"
      },
      "type": "stdio"
    }
  }
}

🔑 Replace YOUR_…_KEY_HERE with your real API keys. You can remove keys you don’t use.

2. (Cursor-only) Enable Taskmaster MCP

Open Cursor Settings (Ctrl+Shift+J) ➡ Click on MCP tab on the left ➡ Enable task-master-ai with the toggle

3. (Optional) Configure the models you want to use

In your editor’s AI chat pane, say:

`1`	`Change the main, research and fallback models to <model_name>, <model_name> and <model_name> respectively.`

Table of available models

4. Initialize Task Master

In your editor’s AI chat pane, say:

`1`	`Initialize taskmaster-ai in my project`

5. Make sure you have a PRD (Recommended)

For new projects: Create your PRD at .taskmaster/docs/prd.txt
For existing projects: You can use scripts/prd.txt or migrate with task-master migrate

An example PRD template is available after initialization in .taskmaster/templates/example_prd.txt.

[!NOTE] While a PRD is recommended for complex projects, you can always create individual tasks by asking “Can you help me implement [description of what you want to do]?” in chat.

Always start with a detailed PRD.

The more detailed your PRD, the better the generated tasks will be.

6. Common Commands

Use your AI assistant to:

Parse requirements: Can you parse my PRD at scripts/prd.txt?
Plan next step: What's the next task I should work on?
Implement a task: Can you help me implement task 3?
Expand a task: Can you help me expand task 4?

More examples on how to use Task Master in chat

Option 2: Using Command Line

Installation

# Install globally
npm install -g task-master-ai

# OR install locally within your project
npm install task-master-ai

Initialize a new project

# If installed globally
task-master init

# If installed locally
npx task-master init

This will prompt you for project details and set up a new project with the necessary files and structure.

Common Commands

# Initialize a new project
task-master init

# Parse a PRD and generate tasks
task-master parse-prd your-prd.txt

# List all tasks
task-master list

# Show the next task to work on
task-master next

# Generate task files
task-master generate

Troubleshooting

If `task-master init` doesn’t respond

Try running it with Node directly:

`1`	`node node_modules/claude-task-master/scripts/init.js`

Or clone the repository and run:

1
2
3

git clone https://github.com/eyaltoledano/claude-task-master.git
cd claude-task-master
node scripts/init.js

Contributors

Star History

Licensing

Task Master is licensed under the MIT License with Commons Clause. This means you can:

✅ Allowed:

Use Task Master for any purpose (personal, commercial, academic)
Modify the code
Distribute copies
Create and sell products built using Task Master

❌ Not Allowed:

Sell Task Master itself
Offer Task Master as a hosted service
Create competing products based on Task Master

See the LICENSE file for the complete license text and licensing details for more information.

Google Gemini on Producthunt daily

bytebot

bytebot-ai/bytebot

Bytebot: Open-Source AI Desktop Agent

What is a Desktop Agent?

Why Give AI Its Own Computer?

Complete Task Autonomy

Process Documents

Use Real Applications

Quick Start

Deploy in 2 Minutes

How It Works

Key Features

Example Tasks

Basic Examples

Document Processing

Multi-Application Workflows

Programmatic Control

Create Tasks via API

Direct Desktop Control

Setting Up Your Desktop Agent

1. Deploy Bytebot

2. Configure the Desktop

3. Start Giving Tasks

Use Cases

Business Process Automation

Development & Testing

Research & Analysis

Architecture

Why Self-Host?

Advanced Features

Multiple AI Providers

Enterprise Deployment

Community & Support

Contributing

License

claude-task-master

eyaltoledano/claude-task-master

Task Master

By @eyaltoledano, @RalphEcom & @jasonzhou1993

Documentation

Quick Install for Cursor 1.0+ (One-Click)

Requirements

Quick Start

Option 1: MCP (Recommended)

1. Add your MCP config at the following path depending on your editor

Manual Configuration

Cursor & Windsurf (mcpServers)

VS Code (servers + type)

2. (Cursor-only) Enable Taskmaster MCP

3. (Optional) Configure the models you want to use

4. Initialize Task Master

5. Make sure you have a PRD (Recommended)

6. Common Commands

Option 2: Using Command Line

Installation

Initialize a new project

Common Commands

Troubleshooting

If task-master init doesn’t respond

Contributors

Star History

Licensing

Cursor & Windsurf (`mcpServers`)

VS Code (`servers` + `type`)

If `task-master init` doesn’t respond