Skip to content

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

docs: add Daytona sandbox tools documentation (#5643)

Lorenze Jay13e0e9be6b30
diff --git a/docs/ar/tools/ai-ml/daytona.mdx b/docs/ar/tools/ai-ml/daytona.mdx
new file mode 100644
index 000000000..9447c6a3f
--- /dev/null
+++ b/docs/ar/tools/ai-ml/daytona.mdx
@@ -0,0 +1,180 @@
+---
+title: Daytona Sandbox Tools
+description: Run shell commands, execute Python, and manage files inside isolated [Daytona](https://www.daytona.io/) sandboxes.
+icon: box
+mode: "wide"
+---
+
+# Daytona Sandbox Tools
+
+## Description
+
+The Daytona sandbox tools give CrewAI agents access to isolated, ephemeral compute environments powered by [Daytona](https://www.daytona.io/). Three tools are available so you can give an agent exactly the capabilities it needs:
+
+- **`DaytonaExecTool`** — run any shell command inside a sandbox.
+- **`DaytonaPythonTool`** — execute a block of Python source code inside a sandbox.
+- **`DaytonaFileTool`** — read, write, append, list, delete, and inspect files inside a sandbox.
+
+All three tools share the same sandbox lifecycle controls, so you can mix and match them while keeping state in a single persistent sandbox.
+
+## Installation
+
+```shell
+uv add "crewai-tools[daytona]"
+# or
+pip install "crewai-tools[daytona]"
+```
+
+Set your API key:
+
+```shell
+export DAYTONA_API_KEY="your-api-key"
+```
+
+`DAYTONA_API_URL` and `DAYTONA_TARGET` are also respected if set.
+
+## Sandbox Lifecycle
+
+All three tools inherit lifecycle controls from `DaytonaBaseTool`:
+
+| Mode | How to enable | Sandbox created | Sandbox deleted |
+|------|--------------|-----------------|-----------------|
+| **Ephemeral** (default) | `persistent=False` (default) | On every `_run` call | At the end of that same call |
+| **Persistent** | `persistent=True` | Lazily on first use | At process exit (via `atexit`), or manually via `tool.close()` |
+| **Attach** | `sandbox_id="<id>"` | Never — attaches to an existing sandbox | Never — the tool will not delete a sandbox it did not create |
+
+Ephemeral mode is the safe default: nothing leaks if the agent forgets to clean up. Use persistent mode when you want filesystem state or installed packages to carry across multiple tool calls — this is typical when pairing `DaytonaFileTool` with `DaytonaExecTool`.
+
+## Examples
+
+### One-shot Python execution (ephemeral)
+
+```python Code
+from crewai_tools import DaytonaPythonTool
+
+tool = DaytonaPythonTool()
+result = tool.run(code="print(sum(range(10)))")
+print(result)
+# {"exit_code": 0, "result": "45\n", "artifacts": None}
+```
+
+### Multi-step shell session (persistent)
+
+```python Code
+from crewai_tools import DaytonaExecTool, DaytonaFileTool
+
+exec_tool = DaytonaExecTool(persistent=True)
+file_tool = DaytonaFileTool(persistent=True)
+
+# Install a package, then write and run a script — all in the same sandbox
+exec_tool.run(command="pip install httpx -q")
+file_tool.run(action="write", path="/workspace/fetch.py", content="import httpx; print(httpx.get('https://httpbin.org/get').status_code)")
+exec_tool.run(command="python /workspace/fetch.py")
+```
+
+<Note>
+Each tool instance maintains its own persistent sandbox. To share **one** sandbox across two tools, create the first tool, grab its sandbox id via `tool._persistent_sandbox.id`, and pass it to the second tool via `sandbox_id=...`.
+</Note>
+
+### Attach to an existing sandbox
+
+```python Code
+from crewai_tools import DaytonaExecTool
+
+tool = DaytonaExecTool(sandbox_id="my-long-lived-sandbox")
+result = tool.run(command="ls /workspace")
+```
+
+### Custom sandbox parameters
+
+Pass Daytona's `CreateSandboxFromSnapshotParams` kwargs via `create_params`:
+
+```python Code
+from crewai_tools import DaytonaExecTool
+
+tool = DaytonaExecTool(
+ persistent=True,
+ create_params={
+ "language": "python",
+ "env_vars": {"MY_FLAG": "1"},
+ "labels": {"owner": "crewai-agent"},
+ },
+)
+```
+
+### Agent integration
+
+```python Code
+from crewai import Agent, Task, Crew
+from crewai_tools import DaytonaExecTool, DaytonaPythonTool, DaytonaFileTool
+
+exec_tool = DaytonaExecTool(persistent=True)
+python_tool = DaytonaPythonTool(persistent=True)
+file_tool = DaytonaFileTool(persistent=True)
+
+coder = Agent(
+ role="Sandbox Engineer",
+ goal="Write and run code in an isolated environment",
+ backstory="An engineer who uses Daytona sandboxes to safely execute code and manage files.",
+ tools=[exec_tool, python_tool, file_tool],
+ verbose=True,
+)
+
+task = Task(
+ description="Write a Python script that prints the first 10 Fibonacci numbers, save it to /workspace/fib.py, and run it.",
+ expected_output="The first 10 Fibonacci numbers printed to stdout.",
+ agent=coder,
+)
+
+crew = Crew(agents=[coder], tasks=[task])
+result = crew.kickoff()
+```
+
+## Parameters
+
+### Shared (`DaytonaBaseTool`)
+
+All three tools accept these parameters at initialization:
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `api_key` | `str \| None` | `$DAYTONA_API_KEY` | Daytona API key. Falls back to the `DAYTONA_API_KEY` env var. |
+| `api_url` | `str \| None` | `$DAYTONA_API_URL` | Daytona API URL override. |
+| `target` | `str \| None` | `$DAYTONA_TARGET` | Daytona target region. |
+| `persistent` | `bool` | `False` | Reuse one sandbox across all calls and delete it at process exit. |
+| `sandbox_id` | `str \| None` | `None` | Attach to an existing sandbox by id or name. |
+| `create_params` | `dict \| None` | `None` | Extra kwargs forwarded to `CreateSandboxFromSnapshotParams` (e.g. `language`, `env_vars`, `labels`). |
+| `sandbox_timeout` | `float` | `60.0` | Timeout in seconds for sandbox create/delete operations. |
+
+### `DaytonaExecTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `command` | `str` | ✓ | Shell command to execute. |
+| `cwd` | `str \| None` | | Working directory inside the sandbox. |
+| `env` | `dict[str, str] \| None` | | Extra environment variables for this command. |
+| `timeout` | `int \| None` | | Maximum seconds to wait for the command. |
+
+### `DaytonaPythonTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `code` | `str` | ✓ | Python source code to execute. |
+| `argv` | `list[str] \| None` | | Argument vector forwarded via `CodeRunParams`. |
+| `env` | `dict[str, str] \| None` | | Environment variables forwarded via `CodeRunParams`. |
+| `timeout` | `int \| None` | | Maximum seconds to wait for execution. |
+
+### `DaytonaFileTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `action` | `str` | ✓ | One of: `read`, `write`, `append`, `list`, `delete`, `mkdir`, `info`. |
+| `path` | `str` | ✓ | Absolute path inside the sandbox. |
+| `content` | `str \| None` | | Content to write or append. Required for `append`. |
+| `binary` | `bool` | | If `True`, `content` is base64 on write; returns base64 on read. |
+| `recursive` | `bool` | | For `delete`: remove directories recursively. |
+| `mode` | `str` | | For `mkdir`: octal permission string (default `"0755"`). |
+
+<Tip>
+For files larger than a few KB, create the file first with `action="write"` and empty content, then send the body via multiple `action="append"` calls of ~4 KB each to stay within tool-call payload limits.
+</Tip>
diff --git a/docs/docs.json b/docs/docs.json
index e2e45df6e..cec8dec7b 100644
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -761,7 +761,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -1240,7 +1241,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -1719,7 +1721,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -2198,7 +2201,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -2677,7 +2681,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -3155,7 +3160,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -3632,7 +3638,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -4109,7 +4116,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -4586,7 +4594,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -5065,7 +5074,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -5543,7 +5553,8 @@
"en/tools/ai-ml/llamaindextool",
"en/tools/ai-ml/langchaintool",
"en/tools/ai-ml/ragtool",
- "en/tools/ai-ml/codeinterpretertool"
+ "en/tools/ai-ml/codeinterpretertool",
+ "en/tools/ai-ml/daytona"
]
},
{
@@ -6039,7 +6050,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -6957,7 +6969,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -7416,7 +7429,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -7875,7 +7889,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -8334,7 +8349,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -8792,7 +8808,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -9250,7 +9267,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -9708,7 +9726,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -10165,7 +10184,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -10622,7 +10642,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -11080,7 +11101,8 @@
"pt-BR/tools/ai-ml/llamaindextool",
"pt-BR/tools/ai-ml/langchaintool",
"pt-BR/tools/ai-ml/ragtool",
- "pt-BR/tools/ai-ml/codeinterpretertool"
+ "pt-BR/tools/ai-ml/codeinterpretertool",
+ "pt-BR/tools/ai-ml/daytona"
]
},
{
@@ -12052,7 +12074,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -12524,7 +12547,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -12996,7 +13020,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -13468,7 +13493,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -13940,7 +13966,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -14411,7 +14438,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -14882,7 +14910,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -15353,7 +15382,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -15823,7 +15853,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -16293,7 +16324,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -16764,7 +16796,8 @@
"ko/tools/ai-ml/llamaindextool",
"ko/tools/ai-ml/langchaintool",
"ko/tools/ai-ml/ragtool",
- "ko/tools/ai-ml/codeinterpretertool"
+ "ko/tools/ai-ml/codeinterpretertool",
+ "ko/tools/ai-ml/daytona"
]
},
{
@@ -17737,7 +17770,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
@@ -18209,7 +18243,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
@@ -18681,7 +18716,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
@@ -19153,7 +19189,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
@@ -19625,7 +19662,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
@@ -20096,7 +20134,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
@@ -20567,7 +20606,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
@@ -21038,7 +21078,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
@@ -21508,7 +21549,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
@@ -21978,7 +22020,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
@@ -22449,7 +22492,8 @@
"ar/tools/ai-ml/llamaindextool",
"ar/tools/ai-ml/langchaintool",
"ar/tools/ai-ml/ragtool",
- "ar/tools/ai-ml/codeinterpretertool"
+ "ar/tools/ai-ml/codeinterpretertool",
+ "ar/tools/ai-ml/daytona"
]
},
{
diff --git a/docs/en/tools/ai-ml/daytona.mdx b/docs/en/tools/ai-ml/daytona.mdx
new file mode 100644
index 000000000..9447c6a3f
--- /dev/null
+++ b/docs/en/tools/ai-ml/daytona.mdx
@@ -0,0 +1,180 @@
+---
+title: Daytona Sandbox Tools
+description: Run shell commands, execute Python, and manage files inside isolated [Daytona](https://www.daytona.io/) sandboxes.
+icon: box
+mode: "wide"
+---
+
+# Daytona Sandbox Tools
+
+## Description
+
+The Daytona sandbox tools give CrewAI agents access to isolated, ephemeral compute environments powered by [Daytona](https://www.daytona.io/). Three tools are available so you can give an agent exactly the capabilities it needs:
+
+- **`DaytonaExecTool`** — run any shell command inside a sandbox.
+- **`DaytonaPythonTool`** — execute a block of Python source code inside a sandbox.
+- **`DaytonaFileTool`** — read, write, append, list, delete, and inspect files inside a sandbox.
+
+All three tools share the same sandbox lifecycle controls, so you can mix and match them while keeping state in a single persistent sandbox.
+
+## Installation
+
+```shell
+uv add "crewai-tools[daytona]"
+# or
+pip install "crewai-tools[daytona]"
+```
+
+Set your API key:
+
+```shell
+export DAYTONA_API_KEY="your-api-key"
+```
+
+`DAYTONA_API_URL` and `DAYTONA_TARGET` are also respected if set.
+
+## Sandbox Lifecycle
+
+All three tools inherit lifecycle controls from `DaytonaBaseTool`:
+
+| Mode | How to enable | Sandbox created | Sandbox deleted |
+|------|--------------|-----------------|-----------------|
+| **Ephemeral** (default) | `persistent=False` (default) | On every `_run` call | At the end of that same call |
+| **Persistent** | `persistent=True` | Lazily on first use | At process exit (via `atexit`), or manually via `tool.close()` |
+| **Attach** | `sandbox_id="<id>"` | Never — attaches to an existing sandbox | Never — the tool will not delete a sandbox it did not create |
+
+Ephemeral mode is the safe default: nothing leaks if the agent forgets to clean up. Use persistent mode when you want filesystem state or installed packages to carry across multiple tool calls — this is typical when pairing `DaytonaFileTool` with `DaytonaExecTool`.
+
+## Examples
+
+### One-shot Python execution (ephemeral)
+
+```python Code
+from crewai_tools import DaytonaPythonTool
+
+tool = DaytonaPythonTool()
+result = tool.run(code="print(sum(range(10)))")
+print(result)
+# {"exit_code": 0, "result": "45\n", "artifacts": None}
+```
+
+### Multi-step shell session (persistent)
+
+```python Code
+from crewai_tools import DaytonaExecTool, DaytonaFileTool
+
+exec_tool = DaytonaExecTool(persistent=True)
+file_tool = DaytonaFileTool(persistent=True)
+
+# Install a package, then write and run a script — all in the same sandbox
+exec_tool.run(command="pip install httpx -q")
+file_tool.run(action="write", path="/workspace/fetch.py", content="import httpx; print(httpx.get('https://httpbin.org/get').status_code)")
+exec_tool.run(command="python /workspace/fetch.py")
+```
+
+<Note>
+Each tool instance maintains its own persistent sandbox. To share **one** sandbox across two tools, create the first tool, grab its sandbox id via `tool._persistent_sandbox.id`, and pass it to the second tool via `sandbox_id=...`.
+</Note>
+
+### Attach to an existing sandbox
+
+```python Code
+from crewai_tools import DaytonaExecTool
+
+tool = DaytonaExecTool(sandbox_id="my-long-lived-sandbox")
+result = tool.run(command="ls /workspace")
+```
+
+### Custom sandbox parameters
+
+Pass Daytona's `CreateSandboxFromSnapshotParams` kwargs via `create_params`:
+
+```python Code
+from crewai_tools import DaytonaExecTool
+
+tool = DaytonaExecTool(
+ persistent=True,
+ create_params={
+ "language": "python",
+ "env_vars": {"MY_FLAG": "1"},
+ "labels": {"owner": "crewai-agent"},
+ },
+)
+```
+
+### Agent integration
+
+```python Code
+from crewai import Agent, Task, Crew
+from crewai_tools import DaytonaExecTool, DaytonaPythonTool, DaytonaFileTool
+
+exec_tool = DaytonaExecTool(persistent=True)
+python_tool = DaytonaPythonTool(persistent=True)
+file_tool = DaytonaFileTool(persistent=True)
+
+coder = Agent(
+ role="Sandbox Engineer",
+ goal="Write and run code in an isolated environment",
+ backstory="An engineer who uses Daytona sandboxes to safely execute code and manage files.",
+ tools=[exec_tool, python_tool, file_tool],
+ verbose=True,
+)
+
+task = Task(
+ description="Write a Python script that prints the first 10 Fibonacci numbers, save it to /workspace/fib.py, and run it.",
+ expected_output="The first 10 Fibonacci numbers printed to stdout.",
+ agent=coder,
+)
+
+crew = Crew(agents=[coder], tasks=[task])
+result = crew.kickoff()
+```
+
+## Parameters
+
+### Shared (`DaytonaBaseTool`)
+
+All three tools accept these parameters at initialization:
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `api_key` | `str \| None` | `$DAYTONA_API_KEY` | Daytona API key. Falls back to the `DAYTONA_API_KEY` env var. |
+| `api_url` | `str \| None` | `$DAYTONA_API_URL` | Daytona API URL override. |
+| `target` | `str \| None` | `$DAYTONA_TARGET` | Daytona target region. |
+| `persistent` | `bool` | `False` | Reuse one sandbox across all calls and delete it at process exit. |
+| `sandbox_id` | `str \| None` | `None` | Attach to an existing sandbox by id or name. |
+| `create_params` | `dict \| None` | `None` | Extra kwargs forwarded to `CreateSandboxFromSnapshotParams` (e.g. `language`, `env_vars`, `labels`). |
+| `sandbox_timeout` | `float` | `60.0` | Timeout in seconds for sandbox create/delete operations. |
+
+### `DaytonaExecTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `command` | `str` | ✓ | Shell command to execute. |
+| `cwd` | `str \| None` | | Working directory inside the sandbox. |
+| `env` | `dict[str, str] \| None` | | Extra environment variables for this command. |
+| `timeout` | `int \| None` | | Maximum seconds to wait for the command. |
+
+### `DaytonaPythonTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `code` | `str` | ✓ | Python source code to execute. |
+| `argv` | `list[str] \| None` | | Argument vector forwarded via `CodeRunParams`. |
+| `env` | `dict[str, str] \| None` | | Environment variables forwarded via `CodeRunParams`. |
+| `timeout` | `int \| None` | | Maximum seconds to wait for execution. |
+
+### `DaytonaFileTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `action` | `str` | ✓ | One of: `read`, `write`, `append`, `list`, `delete`, `mkdir`, `info`. |
+| `path` | `str` | ✓ | Absolute path inside the sandbox. |
+| `content` | `str \| None` | | Content to write or append. Required for `append`. |
+| `binary` | `bool` | | If `True`, `content` is base64 on write; returns base64 on read. |
+| `recursive` | `bool` | | For `delete`: remove directories recursively. |
+| `mode` | `str` | | For `mkdir`: octal permission string (default `"0755"`). |
+
+<Tip>
+For files larger than a few KB, create the file first with `action="write"` and empty content, then send the body via multiple `action="append"` calls of ~4 KB each to stay within tool-call payload limits.
+</Tip>
diff --git a/docs/ko/tools/ai-ml/daytona.mdx b/docs/ko/tools/ai-ml/daytona.mdx
new file mode 100644
index 000000000..9447c6a3f
--- /dev/null
+++ b/docs/ko/tools/ai-ml/daytona.mdx
@@ -0,0 +1,180 @@
+---
+title: Daytona Sandbox Tools
+description: Run shell commands, execute Python, and manage files inside isolated [Daytona](https://www.daytona.io/) sandboxes.
+icon: box
+mode: "wide"
+---
+
+# Daytona Sandbox Tools
+
+## Description
+
+The Daytona sandbox tools give CrewAI agents access to isolated, ephemeral compute environments powered by [Daytona](https://www.daytona.io/). Three tools are available so you can give an agent exactly the capabilities it needs:
+
+- **`DaytonaExecTool`** — run any shell command inside a sandbox.
+- **`DaytonaPythonTool`** — execute a block of Python source code inside a sandbox.
+- **`DaytonaFileTool`** — read, write, append, list, delete, and inspect files inside a sandbox.
+
+All three tools share the same sandbox lifecycle controls, so you can mix and match them while keeping state in a single persistent sandbox.
+
+## Installation
+
+```shell
+uv add "crewai-tools[daytona]"
+# or
+pip install "crewai-tools[daytona]"
+```
+
+Set your API key:
+
+```shell
+export DAYTONA_API_KEY="your-api-key"
+```
+
+`DAYTONA_API_URL` and `DAYTONA_TARGET` are also respected if set.
+
+## Sandbox Lifecycle
+
+All three tools inherit lifecycle controls from `DaytonaBaseTool`:
+
+| Mode | How to enable | Sandbox created | Sandbox deleted |
+|------|--------------|-----------------|-----------------|
+| **Ephemeral** (default) | `persistent=False` (default) | On every `_run` call | At the end of that same call |
+| **Persistent** | `persistent=True` | Lazily on first use | At process exit (via `atexit`), or manually via `tool.close()` |
+| **Attach** | `sandbox_id="<id>"` | Never — attaches to an existing sandbox | Never — the tool will not delete a sandbox it did not create |
+
+Ephemeral mode is the safe default: nothing leaks if the agent forgets to clean up. Use persistent mode when you want filesystem state or installed packages to carry across multiple tool calls — this is typical when pairing `DaytonaFileTool` with `DaytonaExecTool`.
+
+## Examples
+
+### One-shot Python execution (ephemeral)
+
+```python Code
+from crewai_tools import DaytonaPythonTool
+
+tool = DaytonaPythonTool()
+result = tool.run(code="print(sum(range(10)))")
+print(result)
+# {"exit_code": 0, "result": "45\n", "artifacts": None}
+```
+
+### Multi-step shell session (persistent)
+
+```python Code
+from crewai_tools import DaytonaExecTool, DaytonaFileTool
+
+exec_tool = DaytonaExecTool(persistent=True)
+file_tool = DaytonaFileTool(persistent=True)
+
+# Install a package, then write and run a script — all in the same sandbox
+exec_tool.run(command="pip install httpx -q")
+file_tool.run(action="write", path="/workspace/fetch.py", content="import httpx; print(httpx.get('https://httpbin.org/get').status_code)")
+exec_tool.run(command="python /workspace/fetch.py")
+```
+
+<Note>
+Each tool instance maintains its own persistent sandbox. To share **one** sandbox across two tools, create the first tool, grab its sandbox id via `tool._persistent_sandbox.id`, and pass it to the second tool via `sandbox_id=...`.
+</Note>
+
+### Attach to an existing sandbox
+
+```python Code
+from crewai_tools import DaytonaExecTool
+
+tool = DaytonaExecTool(sandbox_id="my-long-lived-sandbox")
+result = tool.run(command="ls /workspace")
+```
+
+### Custom sandbox parameters
+
+Pass Daytona's `CreateSandboxFromSnapshotParams` kwargs via `create_params`:
+
+```python Code
+from crewai_tools import DaytonaExecTool
+
+tool = DaytonaExecTool(
+ persistent=True,
+ create_params={
+ "language": "python",
+ "env_vars": {"MY_FLAG": "1"},
+ "labels": {"owner": "crewai-agent"},
+ },
+)
+```
+
+### Agent integration
+
+```python Code
+from crewai import Agent, Task, Crew
+from crewai_tools import DaytonaExecTool, DaytonaPythonTool, DaytonaFileTool
+
+exec_tool = DaytonaExecTool(persistent=True)
+python_tool = DaytonaPythonTool(persistent=True)
+file_tool = DaytonaFileTool(persistent=True)
+
+coder = Agent(
+ role="Sandbox Engineer",
+ goal="Write and run code in an isolated environment",
+ backstory="An engineer who uses Daytona sandboxes to safely execute code and manage files.",
+ tools=[exec_tool, python_tool, file_tool],
+ verbose=True,
+)
+
+task = Task(
+ description="Write a Python script that prints the first 10 Fibonacci numbers, save it to /workspace/fib.py, and run it.",
+ expected_output="The first 10 Fibonacci numbers printed to stdout.",
+ agent=coder,
+)
+
+crew = Crew(agents=[coder], tasks=[task])
+result = crew.kickoff()
+```
+
+## Parameters
+
+### Shared (`DaytonaBaseTool`)
+
+All three tools accept these parameters at initialization:
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `api_key` | `str \| None` | `$DAYTONA_API_KEY` | Daytona API key. Falls back to the `DAYTONA_API_KEY` env var. |
+| `api_url` | `str \| None` | `$DAYTONA_API_URL` | Daytona API URL override. |
+| `target` | `str \| None` | `$DAYTONA_TARGET` | Daytona target region. |
+| `persistent` | `bool` | `False` | Reuse one sandbox across all calls and delete it at process exit. |
+| `sandbox_id` | `str \| None` | `None` | Attach to an existing sandbox by id or name. |
+| `create_params` | `dict \| None` | `None` | Extra kwargs forwarded to `CreateSandboxFromSnapshotParams` (e.g. `language`, `env_vars`, `labels`). |
+| `sandbox_timeout` | `float` | `60.0` | Timeout in seconds for sandbox create/delete operations. |
+
+### `DaytonaExecTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `command` | `str` | ✓ | Shell command to execute. |
+| `cwd` | `str \| None` | | Working directory inside the sandbox. |
+| `env` | `dict[str, str] \| None` | | Extra environment variables for this command. |
+| `timeout` | `int \| None` | | Maximum seconds to wait for the command. |
+
+### `DaytonaPythonTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `code` | `str` | ✓ | Python source code to execute. |
+| `argv` | `list[str] \| None` | | Argument vector forwarded via `CodeRunParams`. |
+| `env` | `dict[str, str] \| None` | | Environment variables forwarded via `CodeRunParams`. |
+| `timeout` | `int \| None` | | Maximum seconds to wait for execution. |
+
+### `DaytonaFileTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `action` | `str` | ✓ | One of: `read`, `write`, `append`, `list`, `delete`, `mkdir`, `info`. |
+| `path` | `str` | ✓ | Absolute path inside the sandbox. |
+| `content` | `str \| None` | | Content to write or append. Required for `append`. |
+| `binary` | `bool` | | If `True`, `content` is base64 on write; returns base64 on read. |
+| `recursive` | `bool` | | For `delete`: remove directories recursively. |
+| `mode` | `str` | | For `mkdir`: octal permission string (default `"0755"`). |
+
+<Tip>
+For files larger than a few KB, create the file first with `action="write"` and empty content, then send the body via multiple `action="append"` calls of ~4 KB each to stay within tool-call payload limits.
+</Tip>
diff --git a/docs/pt-BR/tools/ai-ml/daytona.mdx b/docs/pt-BR/tools/ai-ml/daytona.mdx
new file mode 100644
index 000000000..9447c6a3f
--- /dev/null
+++ b/docs/pt-BR/tools/ai-ml/daytona.mdx
@@ -0,0 +1,180 @@
+---
+title: Daytona Sandbox Tools
+description: Run shell commands, execute Python, and manage files inside isolated [Daytona](https://www.daytona.io/) sandboxes.
+icon: box
+mode: "wide"
+---
+
+# Daytona Sandbox Tools
+
+## Description
+
+The Daytona sandbox tools give CrewAI agents access to isolated, ephemeral compute environments powered by [Daytona](https://www.daytona.io/). Three tools are available so you can give an agent exactly the capabilities it needs:
+
+- **`DaytonaExecTool`** — run any shell command inside a sandbox.
+- **`DaytonaPythonTool`** — execute a block of Python source code inside a sandbox.
+- **`DaytonaFileTool`** — read, write, append, list, delete, and inspect files inside a sandbox.
+
+All three tools share the same sandbox lifecycle controls, so you can mix and match them while keeping state in a single persistent sandbox.
+
+## Installation
+
+```shell
+uv add "crewai-tools[daytona]"
+# or
+pip install "crewai-tools[daytona]"
+```
+
+Set your API key:
+
+```shell
+export DAYTONA_API_KEY="your-api-key"
+```
+
+`DAYTONA_API_URL` and `DAYTONA_TARGET` are also respected if set.
+
+## Sandbox Lifecycle
+
+All three tools inherit lifecycle controls from `DaytonaBaseTool`:
+
+| Mode | How to enable | Sandbox created | Sandbox deleted |
+|------|--------------|-----------------|-----------------|
+| **Ephemeral** (default) | `persistent=False` (default) | On every `_run` call | At the end of that same call |
+| **Persistent** | `persistent=True` | Lazily on first use | At process exit (via `atexit`), or manually via `tool.close()` |
+| **Attach** | `sandbox_id="<id>"` | Never — attaches to an existing sandbox | Never — the tool will not delete a sandbox it did not create |
+
+Ephemeral mode is the safe default: nothing leaks if the agent forgets to clean up. Use persistent mode when you want filesystem state or installed packages to carry across multiple tool calls — this is typical when pairing `DaytonaFileTool` with `DaytonaExecTool`.
+
+## Examples
+
+### One-shot Python execution (ephemeral)
+
+```python Code
+from crewai_tools import DaytonaPythonTool
+
+tool = DaytonaPythonTool()
+result = tool.run(code="print(sum(range(10)))")
+print(result)
+# {"exit_code": 0, "result": "45\n", "artifacts": None}
+```
+
+### Multi-step shell session (persistent)
+
+```python Code
+from crewai_tools import DaytonaExecTool, DaytonaFileTool
+
+exec_tool = DaytonaExecTool(persistent=True)
+file_tool = DaytonaFileTool(persistent=True)
+
+# Install a package, then write and run a script — all in the same sandbox
+exec_tool.run(command="pip install httpx -q")
+file_tool.run(action="write", path="/workspace/fetch.py", content="import httpx; print(httpx.get('https://httpbin.org/get').status_code)")
+exec_tool.run(command="python /workspace/fetch.py")
+```
+
+<Note>
+Each tool instance maintains its own persistent sandbox. To share **one** sandbox across two tools, create the first tool, grab its sandbox id via `tool._persistent_sandbox.id`, and pass it to the second tool via `sandbox_id=...`.
+</Note>
+
+### Attach to an existing sandbox
+
+```python Code
+from crewai_tools import DaytonaExecTool
+
+tool = DaytonaExecTool(sandbox_id="my-long-lived-sandbox")
+result = tool.run(command="ls /workspace")
+```
+
+### Custom sandbox parameters
+
+Pass Daytona's `CreateSandboxFromSnapshotParams` kwargs via `create_params`:
+
+```python Code
+from crewai_tools import DaytonaExecTool
+
+tool = DaytonaExecTool(
+ persistent=True,
+ create_params={
+ "language": "python",
+ "env_vars": {"MY_FLAG": "1"},
+ "labels": {"owner": "crewai-agent"},
+ },
+)
+```
+
+### Agent integration
+
+```python Code
+from crewai import Agent, Task, Crew
+from crewai_tools import DaytonaExecTool, DaytonaPythonTool, DaytonaFileTool
+
+exec_tool = DaytonaExecTool(persistent=True)
+python_tool = DaytonaPythonTool(persistent=True)
+file_tool = DaytonaFileTool(persistent=True)
+
+coder = Agent(
+ role="Sandbox Engineer",
+ goal="Write and run code in an isolated environment",
+ backstory="An engineer who uses Daytona sandboxes to safely execute code and manage files.",
+ tools=[exec_tool, python_tool, file_tool],
+ verbose=True,
+)
+
+task = Task(
+ description="Write a Python script that prints the first 10 Fibonacci numbers, save it to /workspace/fib.py, and run it.",
+ expected_output="The first 10 Fibonacci numbers printed to stdout.",
+ agent=coder,
+)
+
+crew = Crew(agents=[coder], tasks=[task])
+result = crew.kickoff()
+```
+
+## Parameters
+
+### Shared (`DaytonaBaseTool`)
+
+All three tools accept these parameters at initialization:
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `api_key` | `str \| None` | `$DAYTONA_API_KEY` | Daytona API key. Falls back to the `DAYTONA_API_KEY` env var. |
+| `api_url` | `str \| None` | `$DAYTONA_API_URL` | Daytona API URL override. |
+| `target` | `str \| None` | `$DAYTONA_TARGET` | Daytona target region. |
+| `persistent` | `bool` | `False` | Reuse one sandbox across all calls and delete it at process exit. |
+| `sandbox_id` | `str \| None` | `None` | Attach to an existing sandbox by id or name. |
+| `create_params` | `dict \| None` | `None` | Extra kwargs forwarded to `CreateSandboxFromSnapshotParams` (e.g. `language`, `env_vars`, `labels`). |
+| `sandbox_timeout` | `float` | `60.0` | Timeout in seconds for sandbox create/delete operations. |
+
+### `DaytonaExecTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `command` | `str` | ✓ | Shell command to execute. |
+| `cwd` | `str \| None` | | Working directory inside the sandbox. |
+| `env` | `dict[str, str] \| None` | | Extra environment variables for this command. |
+| `timeout` | `int \| None` | | Maximum seconds to wait for the command. |
+
+### `DaytonaPythonTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `code` | `str` | ✓ | Python source code to execute. |
+| `argv` | `list[str] \| None` | | Argument vector forwarded via `CodeRunParams`. |
+| `env` | `dict[str, str] \| None` | | Environment variables forwarded via `CodeRunParams`. |
+| `timeout` | `int \| None` | | Maximum seconds to wait for execution. |
+
+### `DaytonaFileTool`
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `action` | `str` | ✓ | One of: `read`, `write`, `append`, `list`, `delete`, `mkdir`, `info`. |
+| `path` | `str` | ✓ | Absolute path inside the sandbox. |
+| `content` | `str \| None` | | Content to write or append. Required for `append`. |
+| `binary` | `bool` | | If `True`, `content` is base64 on write; returns base64 on read. |
+| `recursive` | `bool` | | For `delete`: remove directories recursively. |
+| `mode` | `str` | | For `mkdir`: octal permission string (default `"0755"`). |
+
+<Tip>
+For files larger than a few KB, create the file first with `action="write"` and empty content, then send the body via multiple `action="append"` calls of ~4 KB each to stay within tool-call payload limits.
+</Tip>