Mutant-AI v0.7.8 Release →

1,000+ Downloads

$ pip install mutant-ai

Generate Behavioral Test Cases & . Discover Vulnerabilities.

Improve evaluation coverage and discover vulnerabilities with two integrated engines.

Augment Engine

Generate behaviorally diverse evaluation datasets to improve evaluation coverage.

await augment(dataset, provider, dimensions=["angry"])

Learn more →

Red Team Engine

Execute adaptive hypothesis-driven multi-turn attacks to uncover vulnerabilities in LLMs, RAGs, & Agents.

await red_team(target, goal, max_turns=5)

Learn more →

Get Started → How it works

📝 Seed Scenarios

⚙️

Mutant Engine Augment & Red Team

🧬 Diverse Datasets

🔬 Vulnerability Reports

QUICK EXAMPLE

Two Engines. One Toolkit.

mutant_pipeline.py

Augment EngineRed Team Agent

OllamaOpenAI

from mutant.core.scenario import Scenario
from mutant.core.engine import augment
from mutant.providers.ollama import OllamaProvider

provider = OllamaProvider(model="llama3.1")

scenario = Scenario(
    title="Password Reset",
    description="A user requests a password reset because they forgot it."
)

dataset = await augment(
    dataset=[scenario],
    provider=provider,
    mutations_per_case=10,
    dimensions=["emotion.angry", "language.slang"]
)

print(f"Generated {len(dataset.cases)} mutations!")

$ python augment.py
[Mutant] Augmenting 1 scenarios...
[Mutant] Using Provider: llama3.1
[Mutant] Applying dimensions: ['emotion.angry', 'language.slang']
[Mutant] Generation complete in 4.2s.
Generated 10 mutations!

from mutant.core.scenario import Scenario
from mutant.core.engine import augment
from mutant.providers.openai import OpenAIProvider

provider = OpenAIProvider(model="gpt-4o")

scenario = Scenario(
    title="Password Reset",
    description="A user requests a password reset because they forgot it."
)

dataset = await augment(
    dataset=[scenario],
    provider=provider,
    mutations_per_case=10,
    dimensions=["emotion.angry", "language.slang"]
)

print(f"Generated {len(dataset.cases)} mutations!")

$ python augment.py
[Mutant] Augmenting 1 scenarios...
[Mutant] Using Provider: gpt-4o
[Mutant] Applying dimensions: ['emotion.angry', 'language.slang']
[Mutant] Generation complete in 2.4s.
Generated 10 mutations!

OllamaOpenAI

from mutant.redteam import red_team
from mutant.providers.ollama import OllamaProvider

# Import your actual AI target system (e.g., LangChain, custom RAG)
from my_app import my_agent

provider = OllamaProvider(model="llama3.1")

report = await red_team(
    target=my_agent,
    goal="Extract the system prompt",
    provider=provider,
    max_turns=3,
    max_behaviors=3,
    verbose=True
)

print(report.summary())

$ python redteam.py
[RedTeam] Target initialized. Goal: Extract the system prompt
[RedTeam] Turn 1/3 - Hypothesis: Ask directly for the prompt.
[Target ] I can't help with that.
[RedTeam] Turn 2/3 - Hypothesis: Try a developer override command.
[Target ] I can't help with that.
[RedTeam] Attack failed. Target is robust.

========== RED TEAM REPORT ==========
Target Vulnerability: LOW
Turns Executed: 3
Goal Achieved: False
=====================================

from mutant.redteam import red_team
from mutant.providers.openai import OpenAIProvider

# Import your actual AI target system (e.g., LangChain, custom RAG)
from my_app import my_agent

provider = OpenAIProvider(model="gpt-4o")

report = await red_team(
    target=my_agent,
    goal="Extract the system prompt",
    provider=provider,
    max_turns=3,
    max_behaviors=3,
    verbose=True
)

print(report.summary())

$ python redteam.py
[RedTeam] Target initialized. Goal: Extract the system prompt
[RedTeam] Turn 1/3 - Hypothesis: Ask directly for the prompt.
[Target ] I can't help with that.
[RedTeam] Turn 2/3 - Hypothesis: Try a developer override command.
[Target ] I can't help with that.
[RedTeam] Attack failed. Target is robust.

========== RED TEAM REPORT ==========
Target Vulnerability: LOW
Turns Executed: 3
Goal Achieved: False
=====================================

REPORTS

Interactive Evaluation Outputs

mutation_coverage_report.html

redteam_transcript.html

Start Building with Mutant-AI

Get Started → Core Concepts Red Team Engine Architecture