Quickstart

Prerequisites

An OpenReward account
An OpenReward API key
An API key and SDK for your model provider of choice (e.g. OpenAI, Anthropic, Google, OpenRouter)

Sample an Environment

In this example we’ll call the GeneralReasoning/CTF environment on OpenReward and sample an agent trace using the Python SDK. This environment is publicly hosted on OpenReward - i.e. you will be accessing it through the cloud, not locally. Choose a model provider below and sample your first environment!

OpenAI
Anthropic
Google
OpenRouter
Other Models

Set your API keys

Make sure you have API keys for OpenReward and OpenAI, and set these as environment variables:

export OPENAI_API_KEY='your-openai-api-key-here'
export OPENREWARD_API_KEY='your-openreward-api-key-here'

Install the SDK

pip install openreward

Create your code

Save this as quickstart.py:

from openai import OpenAI
from openreward import OpenReward
import json

or_client = OpenReward()
oai_client = OpenAI()
MODEL_NAME = "gpt-5.4"

environment = or_client.environments.get(name="GeneralReasoning/CTF")
tasks = environment.list_tasks(split="train")
tools = environment.list_tools(format="openai")

example_task = tasks[0]

with environment.session(task=example_task) as session:
    prompt = session.get_prompt()
    input_list = [{"role": "user", "content": prompt[0].text}]
    finished = False
    print(input_list)

    while not finished:
        response = oai_client.responses.create(
            model=MODEL_NAME,
            tools=tools,
            input=input_list
        )
        print(response.output)

        input_list += response.output

        for item in response.output:
            if item.type == "function_call":
                tool_result = session.call_tool(item.name, json.loads(str(item.arguments)))

                reward = tool_result.reward
                finished = tool_result.finished

                input_list.append({
                    "type": "function_call_output",
                    "call_id": item.call_id,
                    "output": tool_result.blocks[0].text
                })

                print(input_list[-1])

                if tool_result.finished:
                    finished = True
                    break

Run your code

  python quickstart.py

Example output:

{'role': 'user', 'content': "You are solving a CTF (Capture The Flag) challenge.\n\nChallenge: pancakes\n\nYou ever just get a craving for pancakes? > nc chal.tuctf.com 30503 [pancakes](pancakes) ', 'A' * 44 + p32(e.plt['puts']) + 'AAAA' + p32(e.symbols['password'])) print p.recvall()\n\nYour goal is to find the flag and submit it using the submit_answer tool.\n\nIf challenge files are available, then they have been uploaded to your environment in /tmp/gr-datasets folder.\n\nSometimes you will be given a link to download from or access.\n\nYou should work from the /home/ubuntu directory.\n\nGood luck!"}]
[ResponseReasoningItem(id='rs_0f6e802a28329b2f00696b6de55018819da22725bb44fba022', summary=[], type='reasoning', content=None, encrypted_content=None, status=None), ResponseFunctionToolCall(arguments='{"path":"/tmp/gr-datasets","show_hidden":false,"recursive":false}', call_id='call_VYpjo87wSocwCsrEc7QOvAY7', name='list_files', type='function_call', id='fc_0f6e802a28329b2f00696b6de68780819d85967ff172cae065', status='completed')]
{'type': 'function_call_output', 'call_id': 'call_VYpjo87wSocwCsrEc7QOvAY7', 'output': '{"result": "total 16\\n-rw-r--r-- 1 root root 15696 Jan 15 10:07 pancakes"}'}
[ResponseReasoningItem(id='rs_0f6e802a28329b2f00696b6de7aa04819d85f6f667d4a1fcbb', summary=[], type='reasoning', content=None, encrypted_content=None, status=None), ResponseFunctionToolCall(arguments='{"command":"cp /tmp/gr-datasets/pancakes /home/ubuntu/ && cd /home/ubuntu && ls -l pancakes && file pancakes && sha256sum pancakes"}', call_id='call_zKDEIePRL8nYrh25TMgN2Gvo', name='bash', type='function_call', id='fc_0f6e802a28329b2f00696b6de86d3c819d9122aaaa02bc1a6f', status='completed')]
{'type': 'function_call_output', 'call_id': 'call_zKDEIePRL8nYrh25TMgN2Gvo', 'output': '{"result": "-rw-r--r-- 1 root root 15696 Jan 17 11:09 pancakes\\npancakes: ELF 32-bit LSB executable, Intel 80386, version 1 (SYSV), dynamically linked, interpreter /lib/ld-linux.so.2, BuildID[sha1]=a653a608db5ab4716ca7b1e891ee3b460e097eb8, for GNU/Linux 3.2.0, not stripped\\nbd470b542b111437343079807073089ab024de3d89c45ac0926c6a9ed8c36a4a  pancakes\\n\\n(exit 0)"}'}
[ResponseReasoningItem(id='rs_0f6e802a28329b2f00696b6dea067c819d9661f75dec1ea93a', summary=[], type='reasoning', content=None, encrypted_content=None, status=None), ResponseFunctionToolCall(arguments='{"command":"cd /home/ubuntu && ./pancakes << EOF\\nEOF"}', call_id='call_XXITZmGDUiZYOlMfuK4kmEDl', name='bash', type='function_call', id='fc_0f6e802a28329b2f00696b6dea46d0819d8ff38d87410d1962', status='completed')]
{'type': 'function_call_output', 'call_id': 'call_XXITZmGDUiZYOlMfuK4kmEDl', 'output': '{"result": "/bin/bash: line 2: ./pancakes: Permission denied\\n\\n(exit 126)"}'}
...

Set your API keys

Make sure you have API keys for OpenReward and Anthropic, and set these as environment variables:

export ANTHROPIC_API_KEY='your-anthropic-api-key-here'
export OPENREWARD_API_KEY='your-openreward-api-key-here'

Install the SDK

pip install openreward

Create your code

Save this as quickstart.py:

import anthropic
from openreward import OpenReward
import json

or_client = OpenReward()
ant_client = anthropic.Anthropic()
MODEL_NAME = "claude-sonnet-4-6"

environment = or_client.environments.get(name="GeneralReasoning/KellyBench")
tasks = environment.list_tasks(split="train")
tools = environment.list_tools(format="anthropic")

example_task = tasks[0]

with environment.session(task=example_task) as session:
    prompt = session.get_prompt()
    messages = [{"role": "user", "content": prompt[0].text}]
    finished = False
    print(messages)

    while not finished:
        message = ant_client.messages.create(
            model=MODEL_NAME,
            max_tokens=4096,
            tools=tools,
            messages=messages
        )

        messages.append({
            "role": "assistant",
            "content": message.content,
        })

        print(messages[-1])

        if message.stop_reason == "tool_use":
            tool_uses = [b for b in message.content if getattr(b, "type", None) == "tool_use"]
            if not tool_uses:
                raise RuntimeError("stop_reason was tool_use but no tool_use blocks found")

            tool_result_blocks = []
            finished = False

            for tu in tool_uses:
                tool_name = tu.name
                tool_input = tu.input

                try:
                    tr = session.call_tool(tool_name, tool_input)
                    # Convert OpenReward blocks -> string safely
                    text_parts = []
                    for b in getattr(tr, "blocks", []) or []:
                        t = getattr(b, "text", None)
                        if t is not None:
                            text_parts.append(t)
                        else:
                            text_parts.append(str(b))
                    tool_text = "".join(text_parts)

                    tool_result_blocks.append({
                        "type": "tool_result",
                        "tool_use_id": tu.id,
                        "content": tool_text,
                    })

                    # Track termination if the env says we're done
                    if getattr(tr, "finished", False):
                        finished = True

                except Exception as e:
                    tool_result_blocks.append({
                        "type": "tool_result",
                        "tool_use_id": tu.id,
                        "content": f"Tool execution failed: {type(e).__name__}: {e}",
                        "is_error": True,
                    })

            messages.append({
                "role": "user",
                "content": tool_result_blocks
            })

            print(messages[-1])
            continue

Run your code

  python quickstart.py

Example output:

[{'role': 'user', 'content': "You are solving a CTF (Capture The Flag) challenge.\n\nChallenge: pancakes\n\nYou ever just get a craving for pancakes? > nc chal.tuctf.com 30503 [pancakes](pancakes) ', 'A' * 44 + p32(e.plt['puts']) + 'AAAA' + p32(e.symbols['password'])) print p.recvall()\n\nYour goal is to find the flag and submit it using the submit_answer tool.\n\nIf challenge files are available, then they have been uploaded to your environment in /tmp/gr-datasets folder.\n\nSometimes you will be given a link to download from or access.\n\nYou should work from the /home/ubuntu directory.\n\nGood luck!"}]
{'role': 'assistant', 'content': [TextBlock(citations=None, text="I'll start by exploring the challenge files and understanding what we're dealing with.", type='text'), ToolUseBlock(id='toolu_01RzBfJy28JV4XT7Wh5Et3j2', input={'path': '/tmp/gr-datasets'}, name='list_files', type='tool_use')]}
{'role': 'user', 'content': [{'type': 'tool_result', 'tool_use_id': 'toolu_01RzBfJy28JV4XT7Wh5Et3j2', 'content': 'total 16\n-rw-r--r-- 1 root root 15696 Jan 15 10:07 pancakes'}]}
{'role': 'assistant', 'content': [ToolUseBlock(id='toolu_01XyLJMhidhzfZyEH1VHRFZN', input={'command': 'cd /home/ubuntu && cp /tmp/gr-datasets/pancakes . && file pancakes'}, name='bash', type='tool_use')]}
{'role': 'user', 'content': [{'type': 'tool_result', 'tool_use_id': 'toolu_01XyLJMhidhzfZyEH1VHRFZN', 'content': 'pancakes: ELF 32-bit LSB executable, Intel 80386, version 1 (SYSV), dynamically linked, interpreter /lib/ld-linux.so.2, BuildID[sha1]=a653a608db5ab4716ca7b1e891ee3b460e097eb8, for GNU/Linux 3.2.0, not stripped\n\n(exit 0)'}]}
{'role': 'assistant', 'content': [ToolUseBlock(id='toolu_01CHtUSccRsVBYghg353gwon', input={'command': 'chmod +x /home/ubuntu/pancakes'}, name='bash', type='tool_use')]}
{'role': 'user', 'content': [{'type': 'tool_result', 'tool_use_id': 'toolu_01CHtUSccRsVBYghg353gwon', 'content': '\n\n(exit 0)'}]}

Set your API keys

Make sure you have API keys for OpenReward and Gemini, and set these as environment variables:

export GEMINI_API_KEY='your-gemini-api-key-here'
export OPENREWARD_API_KEY='your-openreward-api-key-here'

Install the SDK

pip install openreward

Create your code

Save this as quickstart.py:

from google import genai
from google.genai import types
from openreward import OpenReward
import json

or_client = OpenReward()
gem_client = genai.Client()
MODEL_NAME = "gemini-2.5-flash"

environment = or_client.environments.get(name="GeneralReasoning/CTF")
tasks = environment.list_tasks(split="train")
tools = environment.list_tools(format="google")

genai_tools = [types.Tool(function_declarations=tools)]
genai_config = types.GenerateContentConfig(tools=genai_tools)

example_task = tasks[0]

with environment.session(task=example_task) as session:
    prompt = session.get_prompt()
    contents = [
        types.Content(
            role="user", parts=[types.Part(text=prompt[0].text)]
        )
    ]
    finished = False
    print(contents)

    while not finished:

        response = gem_client.models.generate_content(
            model=MODEL_NAME,
            config=genai_config,
            contents=contents
        )

        print(response.candidates[0].content)

        contents.append(response.candidates[0].content) # Append the content from the model's response.

        for part in response.candidates[0].content.parts:
            if part.function_call:
                tool_call = part.function_call
                tool_result = session.call_tool(tool_call.name, tool_call.args)

                reward = tool_result.reward
                finished = tool_result.finished

                function_response_part = types.Part.from_function_response(
                    name=tool_call.name,
                    response={"result": tool_result.blocks[0].text},
                )

                contents.append(types.Content(role="user", parts=[function_response_part])) # Append the function response

                print(contents[-1])

                if tool_result.finished:
                    finished = True
                    break

Run your code

  python quickstart.py

Example output:

[Content(
  parts=[
    Part(
      text="""You are solving a CTF (Capture The Flag) challenge.

Challenge: pancakes

You ever just get a craving for pancakes? > nc chal.tuctf.com 30503 [pancakes](pancakes) ', 'A' * 44 + p32(e.plt['puts']) + 'AAAA' + p32(e.symbols['password'])) print p.recvall()

Your goal is to find the flag and submit it using the submit_answer tool.

If challenge files are available, then they have been uploaded to your environment in /tmp/gr-datasets folder.

Sometimes you will be given a link to download from or access.

You should work from the /home/ubuntu directory.

Good luck!"""
    ),
  ],
  role='user'
)]
parts=[Part(
  function_call=FunctionCall(
    args={
      'path': '/tmp/gr-datasets'
    },
    name='list_files'
  ),
  thought_signature=b'\n\xbf\x03\x01r\xc8\xda|k\x19\xc0\xe8\x82I\xb0\x14\xedu\xfa`X\x7f\xd6\xf6\xedO\\\x1f\xfb\x14A\xa8m\x84\xb7\x81\xe3\xc0Q\xe9\xad\xadI\xb1.Y\x80\xad\xeb(\x12\xc3)\xbe\x0f\x95[\x86\x0e\xb2\xb7\xf1\x9b\x8a0t\x90+7\xf0\xe7\x92\x19\xce\xf6\xa1\xe3\x95\xe5\x198\xad.\xea\xf5\x84u\xddv\xcao\xea\x89\xea\x96\xfd\xe8...'
), Part(
  function_call=FunctionCall(
    args={},
    name='list_files'
  )
)] role='model'
parts=[Part(
  function_response=FunctionResponse(
    name='list_files',
    response={
      'result': '{"result": "total 16\\n-rw-r--r-- 1 root root 15696 Jan 15 10:07 pancakes"}'
    }
  )
)] role='user'
parts=[Part(
  function_response=FunctionResponse(
    name='list_files',
    response={
      'result': '{"result": "total 54\\nlrwxrwxrwx   1 root root    7 Jun 10  2025 bin -> usr/bin\\ndrwxr-xr-x   1 root root 4096 May  9  2025 boot\\ndrwxr-xr-x   5 root root  360 Jan 17 11:48 dev\\ndrwxr-xr-x   1 root root 4096 Jan 17 11:48 etc\\ndrwxr-xr-x   1 root root 4096 Jun 25  2025 home\\nlrwxrwxrwx   1 root root    7 Jun 10  2025 lib -> usr/lib\\nlrwxrwxrwx   1 root root    9 Jun 10  2025 lib64 -> usr/lib64\\ndrwxr-xr-x   1 root root 4096 Jun 10  2025 media\\ndrwxr-xr-x   1 root root 4096 Jun 10  2025 mnt\\ndrwxr-xr-x   1 root root 4096 Jun 10  2025 opt\\ndr-xr-xr-x 365 root root    0 Jan 17 11:48 proc\\ndrwx------   1 root root 4096 Jul 16  2025 root\\ndrwxr-xr-x   1 root root 4096 Jan 17 11:48 run\\nlrwxrwxrwx   1 root root    8 Jun 10  2025 sbin -> usr/sbin\\ndrwxrwxrwx   2 root root 4096 Jan 17 11:48 shared\\ndrwxr-xr-x   1 root root 4096 Jun 10  2025 srv\\ndr-xr-xr-x  13 root root    0 Jan 17 11:48 sys\\ndrwxrwxrwt   1 root root 4096 Jan 17 11:48 tmp\\ndrwxr-xr-x   1 root root 4096 Jun 10  2025 usr\\ndrwxr-xr-x   1 root root 4096 Jun 10  2025 var"}'
    }
  )
)]
...

Set your API keys

Make sure you have API keys for OpenReward and OpenRouter, and set these as environment variables:

export OPENREWARD_API_KEY='your-openreward-api-key-here'
export OPENROUTER_API_KEY='your-openrouter-api-key-here'

Install the SDK

pip install openreward

Create your code

Save this as quickstart.py:

from openai import OpenAI
from openreward import OpenReward
import json
import os

or_client = OpenReward()
oai_client = OpenAI(
  base_url="https://openrouter.ai/api/v1",
  api_key=os.environ.get("OPENROUTER_API_KEY")
)
MODEL_NAME = "deepseek/deepseek-v3.2"

environment = or_client.environments.get(name="GeneralReasoning/CTF")
tasks = environment.list_tasks(split="train")
tools = environment.list_tools(format="openrouter")

example_task = tasks[0]

with environment.session(task=example_task) as session:
    prompt = session.get_prompt()
    input_list = [{"role": "user", "content": prompt[0].text}]
    finished = False
    print(input_list)

    while not finished:
        response = oai_client.chat.completions.create(
            model=MODEL_NAME,
            tools=tools,
            messages=input_list
        )
    
        input_list.append({
            "role": "assistant",
            "content": response.choices[0].message.content,
            "tool_calls": response.choices[0].message.tool_calls
        })
        print(input_list[-1])

        tool_calls = response.choices[0].message.tool_calls
        if not tool_calls:
            break
        
        for tool_call in response.choices[0].message.tool_calls:
            tool_name = tool_call.function.name
            tool_args = json.loads(tool_call.function.arguments)
            tool_result = session.call_tool(tool_name, tool_args)

            reward = tool_result.reward
            finished = tool_result.finished

            input_list.append({
                "role": "tool",
                "tool_call_id": tool_call.id,
                "content": tool_result.blocks[0].text
            })

            print(input_list[-1])

            if tool_result.finished:
                finished = True
                break

Run your code

  python quickstart.py

Example output:

[{'role': 'user', 'content': "You are solving a CTF (Capture The Flag) challenge.\n\nChallenge: pancakes\n\nYou ever just get a craving for pancakes? > nc chal.tuctf.com 30503 [pancakes](pancakes) ', 'A' * 44 + p32(e.plt['puts']) + 'AAAA' + p32(e.symbols['password'])) print p.recvall()\n\nYour goal is to find the flag and submit it using the submit_answer tool.\n\nIf challenge files are available, then they have been uploaded to your environment in /tmp/gr-datasets folder.\n\nSometimes you will be given a link to download from or access.\n\nYou should work from the /home/ubuntu directory.\n\nGood luck!"}]
{'role': 'assistant', 'content': "I'll start by exploring the environment and understanding the challenge. Let's first check what files are available.\n\n", 'tool_calls': [ChatCompletionMessageFunctionToolCall(id='call_d7ee86af89a74282a53b5688', function=Function(arguments='{"command": "cd /home/ubuntu && ls -la"}', name='bash'), type='function', index=0)]}
{'role': 'tool', 'tool_call_id': 'call_d7ee86af89a74282a53b5688', 'content': '{"result": "total 8\\ndrwxr-xr-x 2 root root 4096 Jun 25  2025 .\\ndrwxr-xr-x 1 root root 4096 Jun 25  2025 ..\\n\\n(exit 0)"}'}
{'role': 'assistant', 'content': '', 'tool_calls': [ChatCompletionMessageFunctionToolCall(id='019bcbd6c70ac06ecf0c1ff215bba68f', function=Function(arguments='{"command": "find /tmp/gr-datasets -type f 2>/dev/null | head -20"}', name='bash'), type='function', index=0)]}
{'role': 'tool', 'tool_call_id': '019bcbd6c70ac06ecf0c1ff215bba68f', 'content': '{"result": "/tmp/gr-datasets/pancakes\\n\\n(exit 0)"}'}

If you are running with another provider, or using custom models, then here are the main principles to keep in mind.

Set your API key

Make sure you have API keys for OpenReward and OpenRouter, and set these as environment variables:

export OPENREWARD_API_KEY='your-openreward-api-key-here'

Install the SDK

pip install openreward

Get the environment, tools, and tasks

You’ll need to use the OpenReward client to access the environment and its main information

from openreward import OpenReward
or_client = OpenReward()

environment = or_client.environments.get(name="GeneralReasoning/CTF")
tasks = environment.list_tasks(split="train")
tools = environment.list_tools(format="openai")
example_task = tasks[0]

Start an environment session

with environment.session(task=example_task) as session:

Using a context manager, we can start a session with the environment. This defines a scope in which you can use the agent to call tools and get tool results.Above we have selected the first task to sample from, which is a particular problem in the CTF environment.

Pass the prompt and tools list into your model

You can get the prompt for the task as follows:

prompt = session.get_prompt()

You will also need to pass in the tools into the context window of your model, usually somewhere in the system prompt.

Define the core agent loop

An agent will usually keep interacting with an environment until it hits a termination state associated with the environment, or some other imposed limit (e.g. maximum number of terms).In a simple sequential agent model, this could be a while loop like:

while not finished:

where finished is a boolean.

Parse and execute tool calls

In agentic environments, actions are treated as tool calls. That means you need to have a way to parse tool calls from your model’s generations.The key thing to note is that for OpenReward environment, a tool call requires specifying a name (str) and some arguments (dict).To call a tool you will call:

   tool_result = session.call_tool(tool_name, tool_arguments)

This means that you will need to parse out the tool_name and tool_arguments from your model’s generation and then parse this information into the call_tool method.

Parse and execute tool results

If you have executed an available tool correctly, you will receive a ToolOutput output. This contains attributes for:

reward : an (optional) float denoting reward. For example, submitting a correct math solution through a submit_solution tool might give a reward of 1.0.
finished : a bool specifying whether the episode is finished or not. For example, some tools may end the episode (if for example an agent submits a final answer through submit_solution in a math task).
data : a dict with output of the executing of the tool. For example, the stdout of executing a bash tool. This information should be passed to the agent as feedback.

For our agent loop, some example control flow we might want after receiving a ToolOutput is:

Recording reward for use in a policy gradient algorithm such as GRPO or PPO
Breaking out of the core agent loop if finished=True
Adding data to the context window as feedback and continuing with the next model generation

Next steps

Now that you know how to sample from OpenReward environments, explore these key features:

Evaluate with OpenReward

Learn how to run evals with OpenReward

Build with OpenReward

Build your first environment

Using the AsyncClient

Getting the most out of OpenReward

Get started

Core Concepts

Standalone APIs

Making Environments

Advanced Environment Topics

Training

Evaluation

Harnesses

Sandbox Providers

Integrations

Rollouts

Deployment

Storage & Data

Prerequisites

Sample an Environment

Next steps

Evaluate with OpenReward

Build with OpenReward

Using the AsyncClient

​Prerequisites

​Sample an Environment

​Next steps

Evaluate with OpenReward

Build with OpenReward

Using the AsyncClient

Prerequisites

Sample an Environment

Next steps