# Daytona — Secure Sandboxes for AI Code Execution

> Elastic infrastructure for running AI-generated code safely. SDKs for Python, TypeScript, Go. By Daytona. 71K+ GitHub stars.

## Install

Copy the content below into your project:

# Daytona — Secure Sandboxes for AI Code Execution

## Quick Use

```bash
pip install daytona-sdk
```

```python
from daytona_sdk import Daytona

daytona = Daytona()

# Create a sandboxed environment
sandbox = daytona.create()

# Execute AI-generated code safely
response = sandbox.process.code_run('print("Hello from sandbox!")')
print(response.result)

# File operations in the sandbox
sandbox.fs.upload_file('/app/script.py', 'print(42 * 42)')
result = sandbox.process.code_run(open('/app/script.py').read())

# Clean up
daytona.remove(sandbox)
```

TypeScript:
```bash
npm install @daytonaio/sdk
```

```typescript
import { Daytona } from '@daytonaio/sdk';

const daytona = new Daytona();
const sandbox = await daytona.create();
const result = await sandbox.process.codeRun('console.log("Hello!")');
console.log(result.result);
```

---

## Intro

Daytona is an open-source infrastructure platform with 71,000+ GitHub stars for securely running AI-generated code. It provides programmatic SDKs (Python, TypeScript, Go, Ruby) to create isolated sandbox environments where untrusted code can execute safely without affecting your host system. Originally a dev environment manager, Daytona evolved into the go-to infrastructure layer for AI agents, coding assistants, and LLM-powered applications that need to run arbitrary code. Each sandbox is fully isolated with its own filesystem, network, and process space.

Works with: Python, TypeScript, Go, Ruby, any AI agent framework (LangChain, CrewAI, AutoGen). Best for teams building AI agents that execute code or AI-powered development tools. Setup time: under 5 minutes.

---

## Daytona Sandbox Architecture

### Core Concepts

| Concept | Description |
|---------|-------------|
| **Sandbox** | Isolated execution environment with its own filesystem and processes |
| **Code Execution** | Run Python, Node.js, or shell commands safely |
| **File System** | Upload, download, and manage files in the sandbox |
| **Git Integration** | Clone repos directly into sandboxes |
| **LSP** | Language Server Protocol for IDE-like features |

### AI Agent Integration

```python
from daytona_sdk import Daytona

def ai_coding_agent(task: str) -> str:
    daytona = Daytona()
    sandbox = daytona.create(language="python")

    # Let the LLM generate code
    code = llm.generate(f"Write Python code to: {task}")

    # Execute safely in sandbox
    result = sandbox.process.code_run(code)

    if result.exit_code == 0:
        return result.result
    else:
        # Let LLM fix the error
        fixed = llm.generate(f"Fix this error: {result.result}")
        return sandbox.process.code_run(fixed).result
```

### Security Features

- **Process isolation** — Each sandbox runs in its own container
- **Network isolation** — Configurable network access per sandbox
- **Resource limits** — CPU, memory, and disk quotas
- **Ephemeral by default** — Sandboxes are destroyed after use
- **No host access** — Sandboxed code cannot reach your host system

### Multi-Language Support

```python
# Python execution
sandbox.process.code_run('import pandas as pd; print(pd.__version__)')

# Node.js execution
sandbox.process.code_run('console.log(process.version)', language='javascript')

# Shell commands
sandbox.process.exec('ls -la /app')
sandbox.process.exec('pip install requests')
```

---

## FAQ

**Q: What is Daytona?**
A: Daytona is an open-source platform with 71,000+ GitHub stars for creating secure sandboxed environments to run AI-generated code safely, with SDKs for Python, TypeScript, Go, and Ruby.

**Q: How is Daytona different from E2B?**
A: Both provide code execution sandboxes. Daytona is fully open-source (AGPL-3.0) and self-hostable. E2B is primarily a cloud service. Daytona also offers Git integration and LSP support for IDE-like features.

**Q: Is Daytona free?**
A: Yes, open-source under AGPL-3.0. Self-host for free. Daytona also offers a managed cloud service.

---

## Source & Thanks

> Created by [Daytona](https://github.com/daytonaio). Licensed under AGPL-3.0.
>
> [daytona](https://github.com/daytonaio/daytona) — ⭐ 71,000+

---

<!-- ZH -->

## 快速使用

```bash
pip install daytona-sdk
```

```python
from daytona_sdk import Daytona
daytona = Daytona()
sandbox = daytona.create()
result = sandbox.process.code_run('print(42 * 42)')
print(result.result)
```

---

## 简介

Daytona 是一个拥有 71,000+ GitHub stars 的开源基础设施平台，专为安全运行 AI 生成的代码而设计。提供 Python、TypeScript、Go、Ruby SDK，创建隔离的沙箱环境执行不受信任的代码。是 AI 代理和编码助手的理想基础设施层。

---

## 来源与感谢

> Created by [Daytona](https://github.com/daytonaio). Licensed under AGPL-3.0.
>
> [daytona](https://github.com/daytonaio/daytona) — ⭐ 71,000+


---
Source: https://tokrepo.com/en/workflows/ab55b619-f3cc-4930-9de3-c99534b5afd3
Author: AI Open Source