Skip to main content

Dreadnode SDK

Project description

Logo

Dreadnode Strikes SDK

PyPI - Python Version PyPI - Version GitHub License Tests Pre-Commit Renovate


Strikes is a platform for building, experimenting with, and evaluating AI security agent code.

  • Experiment + Tasking + Observability in a single place that's lightweight and scales.
  • Track your data with parameters, inputs, and outputs all connected to your tasks.
  • Log your artifacts — data, models, files, and folders — to track data of your Dreadnode runs, enabling easy reuse and reproducibility.
  • Measure everything with metrics throughout your code and anywhere you need them.
  • Scale your code from a single run to thousands.
import dreadnode as dn
import rigging as rg

from .tools import reversing_tools

dn.configure()

@dataclass
class Finding:
    name: str
    severity: str
    description: str
    exploit_code: str

@dn.scorer(name="Score Finding")
async def score_finding(finding: Finding) -> float:
    if finding.severity == "critical":
        return 1.0
    elif finding.severity == "high":
        return 0.8
    else:
        return 0.2

@dn.task(scorers=[score_finding])
@rg.prompt(tools=[reversing_tools])
async def analyze_binary(binary: str) -> list[Finding]:
    """
    Analyze the binary for vulnerabilities.
    """
    ...

with dn.run(tags=["reverse-engineering"]):
    binary = "c2/downloads/service.exe"

    dn.log_params(
        model="gpt-4",
        temperature=0.5,
        binary=binary
    )

    findings = await analyze_binary(binary)

    dn.log_metric("findings", len(findings))

Installation

We publish every version to PyPi:

pip install -U dreadnode

If you want to build from source:

uv sync

# Install with multimodal extras
uv sync --extras multimodal

# Install with training extras
uv sync --extras training

# Install with all extras
uv sync --all-extras

Installation from PyPI with Optional Features

For advanced media processing capabilities (audio, video, images), install the multimodal extras:

# Multimodal support (audio, video processing)
pip install -U "dreadnode[multimodal]"

# Training support (ML model integration)
pip install -U "dreadnode[training]"

# All optional features
pip install -U "dreadnode[all]"

See our installation guide for more options.

Getting Started

Read through our introduction guide in the docs.

Examples

Check out dreadnode/example-agents to find your favorite use case.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dreadnode-1.14.1.tar.gz (253.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

dreadnode-1.14.1-py3-none-any.whl (295.6 kB view details)

Uploaded Python 3

File details

Details for the file dreadnode-1.14.1.tar.gz.

File metadata

  • Download URL: dreadnode-1.14.1.tar.gz
  • Upload date:
  • Size: 253.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for dreadnode-1.14.1.tar.gz
Algorithm Hash digest
SHA256 446b0b24bdd9adbb56ecb75dddbd74e5fe4b4ca074d12cfe34379de57407f06a
MD5 3c6568464fc22fd19c190e0a01afa82d
BLAKE2b-256 1a99c730ace261c56a81f77b8159285b490cd038a9eb29ea2c72790c80db4ab5

See more details on using hashes here.

Provenance

The following attestation bundles were made for dreadnode-1.14.1.tar.gz:

Publisher: publish.yaml on dreadnode/sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file dreadnode-1.14.1-py3-none-any.whl.

File metadata

  • Download URL: dreadnode-1.14.1-py3-none-any.whl
  • Upload date:
  • Size: 295.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for dreadnode-1.14.1-py3-none-any.whl
Algorithm Hash digest
SHA256 82b80d120cb6e8ce7725730796e844ee39ca2222559eec36878f015f0812fdcc
MD5 b4191ab44574b87eb189de0fadfe9f20
BLAKE2b-256 2535bfb7f77ce6f18fd9a885081032fbbcc36caa15f683e8bdb2b32d536efe58

See more details on using hashes here.

Provenance

The following attestation bundles were made for dreadnode-1.14.1-py3-none-any.whl:

Publisher: publish.yaml on dreadnode/sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page