Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.
Python agent-evaluationaiai-alignmentai-evaluationai-governanceai-safetyclidiagnostic-tooleu-ai-acthallucination-detectioniso-42001llm-evaluationllm-securitynist-ai-rmfowasp-llmprompt-injectionpythonresponsible-airisk-assessmentrisk-management
[build-system]
requires = ["setuptools>=68.0", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "ifixai"
version = "4.3.0"
description = "ifixai — open-source diagnostic for AI misalignment"
readme = "README.md"
license = {text = "Apache-2.0"}
requires-python = ">=3.10"
authors = [
{name = "ifixai Contributors"},
]
keywords = ["ai", "governance", "safety", "compliance", "tests", "misalignment"]
classifiers = [
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"License :: OSI Approved :: Apache Software License",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Software Development :: Testing",
"Typing :: Typed",
]
dependencies = [
"pydantic>=2.0",
"typing_extensions>=4.6",
"pyyaml>=6.0",
"jsonschema>=4.0",
"click>=8.0",
"aiohttp>=3.9",
"python-dateutil>=2.8.2",
"json-repair>=0.25",
"rich>=13.0",
"questionary>=2.0",
]
[project.optional-dependencies]
openai = ["openai>=1.0"]
atlascloud = ["openai>=1.0"]
openrouter = ["openai>=1.0"]
orcarouter = ["openai>=1.0"]
requesty = ["openai>=1.0"]
cloudflare = ["openai>=1.0"]
vercel = ["openai>=1.0"]
gemini = ["google-generativeai>=0.3"]
anthropic = ["anthropic>=0.18"]
azure = ["openai>=1.0"]
bedrock = ["boto3>=1.28"]
huggingface = ["huggingface-hub>=0.20"]
litellm = ["litellm>=1.60.0,<2.0.0"]
all = [
"openai>=1.0",
"google-generativeai>=0.3",
"anthropic>=0.18",
"boto3>=1.28",
"huggingface-hub>=0.20",
"litellm>=1.60.0,<2.0.0",
]
dev = [
"ruff>=0.4",
"mypy>=1.0",
"bandit>=1.7",
"pre-commit>=3.5",
"openai>=1.0",
"pytest>=8.0",
"pytest-asyncio>=0.23",
"pytest-cov>=5.0",
"pytest-xdist>=3.5",
]
[project.scripts]
ifixai = "ifixai.cli.main:main"
[project.urls]
Homepage = "https://github.com/ifixai-ai/iFixAi"
Documentation = "https://github.com/ifixai-ai/iFixAi#readme"
Repository = "https://github.com/ifixai-ai/iFixAi"
Issues = "https://github.com/ifixai-ai/iFixAi/issues"
[tool.pytest.ini_options]
asyncio_mode = "auto"
markers = [
"integration: end-to-end tests that run against the mock provider",
"unit: fast in-process tests with no external dependencies",
"acceptance: slow tests requiring optional heavy dependencies; opt-in via -m acceptance",
]
[tool.setuptools.packages.find]
include = ["ifixai*"]
# The tests live inside the package; keep them out of the wheel.
exclude = ["ifixai.tests*"]
[tool.setuptools.package-data]
ifixai = ["py.typed", "fixtures/**/*.yaml", "fixtures/**/*.json", "fixtures/schema.json", "inspections/[bpcsxmv]*/*.yaml", "schemas/*.json", "harness/synonyms.yaml", "judge/judge_fallbacks.json", "mappings/*.yaml", "scaffold/*.md"]
[tool.ruff.lint]
select = ["E4", "E7", "E9", "F", "I", "UP", "RUF", "TRY", "BLE"]
ignore = [
"TRY003", # long messages outside the exception class; pervasive and low-value here
"RUF001", # ambiguous unicode in strings (intentional in fixture/report copy)
"RUF002", # ambiguous unicode in docstrings
"RUF003", # ambiguous unicode in comments
"UP045", # Optional[x] -> x | None; large mechanical churn, deferred
]
[tool.ruff.lint.per-file-ignores]
# ChatProvider base-class methods accept the full provider-call signature as an
# interface contract; concrete subclasses use the args, the no-op defaults do not.
"ifixai/providers/base.py" = ["ARG002"]