Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 30 additions & 28 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,8 +1,10 @@
<div align="center">

<img src="docs/images/bytebot-logo.png" width="500" alt="Bytebot Logo">
<img src="docs/images/bytebot-logo.png" width="500" alt="CUA.kira Logo">

# Bytebot: Open-Source AI Desktop Agent
# CUA.kira: Open-Source AI Desktop Agent

> CUA.kira is an actively maintained fork of [Bytebot](https://github.com/bytebot-ai/bytebot). Until dedicated docs ship, many setup links still point to the upstream project.

<a href="https://trendshift.io/repositories/14624" target="_blank"><img src="https://trendshift.io/api/badge/repositories/14624" alt="bytebot-ai%2Fbytebot | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

Expand All @@ -14,7 +16,7 @@
[![License](https://img.shields.io/badge/license-Apache%202.0-green.svg)](LICENSE)
[![Discord](https://img.shields.io/discord/1232768900274585720?color=7289da&label=discord)](https://discord.com/invite/d9ewZkWPTP)

[🌐 Website](https://bytebot.ai) • [📚 Documentation](https://docs.bytebot.ai) • [💬 Discord](https://discord.com/invite/d9ewZkWPTP) • [𝕏 Twitter](https://x.com/bytebot_ai)
[🌐 Website](https://kira.id) • [📚 Documentation](https://docs.kira.id) • [💬 Discord](https://discord.com/invite/d9ewZkWPTP) • [𝕏 Twitter](https://x.com/bytebot_ai)

<!-- Keep these links. Translations will automatically update with the README. -->
[Deutsch](https://zdoc.app/de/bytebot-ai/bytebot) |
Expand All @@ -35,7 +37,7 @@ 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:
A desktop agent is an AI that has its own computer. Unlike browser-only agents or traditional RPA tools, CUA.kira 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
Expand All @@ -51,7 +53,7 @@ When AI has access to a complete desktop environment, it unlocks capabilities th

### Complete Task Autonomy

Give Bytebot a task like "Download all invoices from our vendor portals and organize them into a folder" and it will:
Give CUA.kira 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
Expand All @@ -61,7 +63,7 @@ Give Bytebot a task like "Download all invoices from our vendor portals and orga

### Process Documents

Upload files directly to Bytebot's desktop and it can:
Upload files directly to CUA.kira's desktop and it can:

- Read entire PDFs into its context
- Extract data from complex documents
Expand All @@ -71,7 +73,7 @@ Upload files directly to Bytebot's desktop and it can:

### Use Real Applications

Bytebot isn't limited to web interfaces. It can:
CUA.kira 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
Expand All @@ -90,8 +92,8 @@ Just click and add your AI provider API key.
**Option 2: Docker Compose**

```bash
git clone https://github.com/bytebot-ai/bytebot.git
cd bytebot
git clone https://github.com/kira-id/cua.kira.git
cd cua.kira

# Add your AI provider key (choose one)
echo "ANTHROPIC_API_KEY=sk-ant-..." > docker/.env
Expand All @@ -103,22 +105,22 @@ docker-compose -f docker/docker-compose.yml up -d
# Open http://localhost:9992
```

[Full deployment guide →](https://docs.bytebot.ai/quickstart)
[Full deployment guide →](https://docs.kira.id/quickstart)

## How It Works

Bytebot consists of four integrated components:
CUA.kira consists of four integrated components:

1. **Virtual Desktop**: A complete Ubuntu Linux environment with pre-installed applications
2. **AI Agent**: Understands your tasks and controls the desktop to complete them
3. **Task Interface**: Web UI where you create tasks and watch Bytebot work
3. **Task Interface**: Web UI where you create tasks and watch CUA.kira work
4. **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
- **File Uploads**: Drop files onto tasks for CUA.kira to process
- **Live Desktop View**: Watch CUA.kira 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
Expand Down Expand Up @@ -183,13 +185,13 @@ curl -X POST http://localhost:9990/computer-use \
-d '{"action": "click_mouse", "coordinate": [500, 300]}'
```

[Full API documentation →](https://docs.bytebot.ai/api-reference/introduction)
[Full API documentation →](https://docs.kira.id/api-reference/introduction)

## Setting Up Your Desktop Agent

### 1. Deploy Bytebot
### 1. Deploy CUA.kira

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

### 2. Configure the Desktop

Expand All @@ -198,11 +200,11 @@ 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
- Log into websites you want CUA.kira to access

### 3. Start Giving Tasks

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

## Use Cases

Expand All @@ -229,7 +231,7 @@ Create tasks in natural language and watch Bytebot complete them using the confi

## Architecture

Bytebot is built with:
CUA.kira is built with:

- **Desktop**: Ubuntu 22.04 with XFCE, Firefox, VS Code, and other tools
- **Agent**: NestJS service that coordinates AI and desktop actions
Expand All @@ -248,7 +250,7 @@ Bytebot is built with:

### Multiple AI Providers

Use any AI provider through our [LiteLLM integration](https://docs.bytebot.ai/deployment/litellm):
Use any AI provider through our [LiteLLM integration](https://docs.kira.id/deployment/litellm):

- Azure OpenAI
- AWS Bedrock
Expand All @@ -261,20 +263,20 @@ Deploy on Kubernetes with Helm:

```bash
# Clone the repository
git clone https://github.com/bytebot-ai/bytebot.git
cd bytebot
git clone https://github.com/kira-id/cua.kira.git
cd cua.kira

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

[Enterprise deployment guide →](https://docs.bytebot.ai/deployment/helm)
[Enterprise deployment guide →](https://docs.kira.id/deployment/helm)

## Community & Support

- **Discord**: [Join our community](https://discord.com/invite/d9ewZkWPTP) for help and discussions
- **Documentation**: Comprehensive guides at [docs.bytebot.ai](https://docs.bytebot.ai)
- **Documentation**: Comprehensive guides at [docs.kira.id](https://docs.kira.id)
- **GitHub Issues**: Report bugs and request features

## Contributing
Expand All @@ -288,14 +290,14 @@ We welcome contributions! Whether it's:

Please:

1. Check existing [issues](https://github.com/bytebot-ai/bytebot/issues) first
1. Check existing [issues](https://github.com/kira-id/cua.kira/issues) first
2. Open an issue to discuss major changes
3. Submit PRs with clear descriptions
4. Join our [Discord](https://discord.com/invite/d9ewZkWPTP) to discuss ideas

## License

Bytebot is open source under the Apache 2.0 license.
CUA.kira is open source under the Apache 2.0 license.

---

Expand Down
8 changes: 8 additions & 0 deletions docker/.env.example
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
# Screenshot compression defaults for bytebot-desktop
SCREENSHOT_COMPRESSION_ENABLED=true
SCREENSHOT_TARGET_SIZE_KB=512
SCREENSHOT_INITIAL_QUALITY=85
SCREENSHOT_MIN_QUALITY=40
SCREENSHOT_MAX_WIDTH=1024
SCREENSHOT_MAX_HEIGHT=768
SCREENSHOT_IMAGE_FORMAT=jpeg
82 changes: 0 additions & 82 deletions docker/docker-compose-claude-code.yml

This file was deleted.

8 changes: 8 additions & 0 deletions docker/docker-compose.proxy.yml
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,14 @@ services:
- ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
- OPENAI_API_KEY=${OPENAI_API_KEY}
- GEMINI_API_KEY=${GEMINI_API_KEY}
- OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
- MISTRAL_API_KEY=${MISTRAL_API_KEY}
- COHERE_API_KEY=${COHERE_API_KEY}
- GROQ_API_KEY=${GROQ_API_KEY}
- PERPLEXITY_API_KEY=${PERPLEXITY_API_KEY}
- TOGETHER_API_KEY=${TOGETHER_API_KEY}
- DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY}
- FIREWORKS_API_KEY=${FIREWORKS_API_KEY}
networks:
- bytebot-network

Expand Down
Loading