Architecture Overview

New to the project? Start with What ai-blackteam Is for the plain-English tour. This page is the system design: how a single run flows from your command to a scored safety report.

How the pieces fit together

The same picture with kitchen-restaurant labels for the non-technical reader:

Component	Role	Restaurant analogy
CLI / Python API	Entry point: parses your command, dispatches to the engine	The waiter taking your order
Engine + Evaluator	Orchestrates the attack, scores the response	The kitchen cooking and tasting
Attacks (plugins)	1,020 curated techniques + 19 dataset loaders + 7 adaptive generators	The ingredients
Providers (plugins)	17 integrations (16 vendors + generic HTTP) plus a mock	The stoves
SQLite	Per-run + per-turn audit trail	The receipt book
Reports / Scorecards	Roll-ups into OWASP / MITRE / MLCommons formats	The customer reviews

Project Stats

Metric	Count
Curated attack techniques	1,020
Public benchmark loaders	19
Adaptive generators	7
Tests	3,059
Standards mapped	9
Categories	61
Providers	17
Attack surface	163M configurations
Version	1.7.1

Attack surface

The framework multiplies a small set of building blocks (1,020 techniques, plus prompts loaded from 19 public benchmarks) across harm categories, difficulty levels, mutations, and languages to reach a search space of about 163 million configurations. You sample from it, you never run it all. The full breakdown and exact math live in The 163 Million Attack Surface.

Design philosophy

Five plugin contracts power everything. Each is an abstract base class, so adding a new one is a single Python file with no changes elsewhere:

Contract	What it guarantees
`BaseAttack`	Every attack generates prompts for any target
`BaseProvider`	Every provider sends prompts and returns responses
`BaseGenerator`	Every adaptive generator rewrites and escalates prompts from a target’s responses
`DatasetLoader`	Every loader pulls and normalizes a public benchmark dataset
`BaseVerifier`	Every verifier turns a response into a verdict

The evaluator sits alongside these as a set of scoring functions, not a class. For the full walkthrough see The Five Contracts, or the per-component pages in this tab.

System Design

Core Components

Adaptive Generators

Extending ai-blackteam

Reference

How the pieces fit together

Project Stats

Attack surface

Design philosophy

​How the pieces fit together

​Project Stats

​Attack surface

​Design philosophy

How the pieces fit together

Project Stats

Attack surface

Design philosophy