Pular para o conteúdo principal

​
Daytona Sandbox Tools

​
Description

The Daytona sandbox tools give CrewAI agents access to isolated, ephemeral compute environments powered by Daytona. 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

uv add "crewai-tools[daytona]"
# or
pip install "crewai-tools[daytona]"
Set your API key: 
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:
ModeHow to enableSandbox createdSandbox deleted
Ephemeral (default)persistent=False (default)On every _run callAt the end of that same call
Persistentpersistent=TrueLazily on first useAt process exit (via atexit), or manually via tool.close()
Attachsandbox_id="<id>"Never — attaches to an existing sandboxNever — 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)

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)

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")
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=....

​
Attach to an existing sandbox

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:
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

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:
ParameterTypeDefaultDescription
api_keystr | None$DAYTONA_API_KEYDaytona API key. Falls back to the DAYTONA_API_KEY env var.
api_urlstr | None$DAYTONA_API_URLDaytona API URL override.
targetstr | None$DAYTONA_TARGETDaytona target region.
persistentboolFalseReuse one sandbox across all calls and delete it at process exit.
sandbox_idstr | NoneNoneAttach to an existing sandbox by id or name.
create_paramsdict | NoneNoneExtra kwargs forwarded to CreateSandboxFromSnapshotParams (e.g. language, env_vars, labels).
sandbox_timeoutfloat60.0Timeout in seconds for sandbox create/delete operations.

​
DaytonaExecTool

ParameterTypeRequiredDescription
commandstr✓Shell command to execute.
cwdstr | NoneWorking directory inside the sandbox.
envdict[str, str] | NoneExtra environment variables for this command.
timeoutint | NoneMaximum seconds to wait for the command.

​
DaytonaPythonTool

ParameterTypeRequiredDescription
codestr✓Python source code to execute.
argvlist[str] | NoneArgument vector forwarded via CodeRunParams.
envdict[str, str] | NoneEnvironment variables forwarded via CodeRunParams.
timeoutint | NoneMaximum seconds to wait for execution.

​
DaytonaFileTool

ParameterTypeRequiredDescription
actionstr✓One of: read, write, append, list, delete, mkdir, info.
pathstr✓Absolute path inside the sandbox.
contentstr | NoneContent to write or append. Required for append.
binaryboolIf True, content is base64 on write; returns base64 on read.
recursiveboolFor delete: remove directories recursively.
modestrFor mkdir: octal permission string (default "0755").
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.