CAMEL’s runtime module enables the secure, flexible, and isolated execution of tools and code. Runtimes allow agents to safely run functions in controlled environments—from in-process security checks to Docker isolation and remote/cloud sandboxes.

​
What are Runtimes?

Modern agent systems often require more than a simple interpreter. Runtimes provide safe, scalable execution via guardrails, isolation, or remote/cloud endpoints—ideal for complex or untrusted code.

LLMGuardRuntime

Guardrail layer for safe function execution.
  • LLM-based risk scoring (1=safe, 3=unsafe)
  • Threshold control for blocking risky calls
  • Pre-configured safety system prompt/tool

DockerRuntime / UbuntuDockerRuntime

Isolated, reproducible containers via Docker.
  • Sandbox tool execution for safety
  • FastAPI server for tool endpoints
  • Ubuntu flavor supports .py script execution, env vars, and more

RemoteHttpRuntime

Remote, distributed execution on HTTP servers.
  • Tool execution via FastAPI HTTP APIs
  • Distribute compute and offload risky code
  • Easy integration with remote endpoints

DaytonaRuntime

Cloud-managed sandboxing with Daytona SDK.
  • Secure remote sandbox per tool
  • Upload, run, and manage source code safely
  • Automated input/output handling

​
Runtime Interface

All runtimes inherit from BaseRuntime, which defines core methods:
  • add(funcs): Register one or more FunctionTool objects for execution
  • reset(): Reset the runtime to its initial state
  • get_tools(): List all tools managed by the runtime

​
Quick Start Example: RemoteHttpRuntime

Remote HTTP Runtime Example

Easily run tools in a remote FastAPI-based runtime—great for scaling, isolation, and experimentation.

from camel.runtimes import RemoteHttpRuntime
from camel.toolkits import MathToolkit

if __name__ == "__main__":
    runtime = (
        RemoteHttpRuntime("localhost")
        .add(MathToolkit().get_tools(), "camel.toolkits.MathToolkit")
        .build()
    )

    print("Waiting for runtime to be ready...")
    runtime.wait()
    print("Runtime is ready.")

    # There are more tools imported from MathToolkit.
    # For simplicity, we use only "add" tool here
    add = runtime.get_tools()[0]
    print(f"Add 1 + 2: {add.func(1, 2)}")
    # Example output:
    # Add 1 + 2: 3

​
Runtime Types: Key Features

​
More Examples

You’ll find runnable scripts for each runtime in examples/runtime/ in our main repo.
Each script demonstrates how to initialize and use a specific runtime—perfect for experimentation or production setups.

​
Final Note

The runtime system primarily sandboxes FunctionTool-style tool functions.
For agent-level, dynamic code execution, always consider dedicated sandboxing—such as UbuntuDockerRuntime’s exec_python_file()—for running dynamically generated scripts with maximum isolation and safety.