iFixAi
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.
File Explorer
Download Latest Version (.zip)- marketplace.json
- marketplace.json
- bug_report.md
- feature_request.md
- ci.yml
- release.yml
- traction.yaml
- CODEOWNERS
- SCORECARD.md
- SCORECARD.md
- SCORECARD.md
- SCORECARD.md
- benchmark_execution.png
- downloads_history.json
- ifixai-banner.png
- ifixai-demo.gif
- installs_runs_chart.png
- pypi_stats_history.json
- runs_history.json
- scorecard-screenshot.png
- cli.md
- fixture_authoring.md
- get-started.md
- inspections.md
- methodology.md
- python-api.md
- README.md
- reproducibility.md
- scoring.md
- testing-your-agent.md
- traction.md
- what-we-test.md
- __init__.py
- _branding.py
- colors.py
- compare.py
- config_file.py
- init.py
- list_cmd.py
- main.py
- model_catalog.py
- orchestrator.py
- reports.py
- run.py
- scaffold.py
- schemas.py
- setup_cmd.py
- ui.py
- validate.py
- __init__.py
- concurrency.py
- connection.py
- context.py
- discovery.py
- fixture_loader.py
- governance_synthesis.py
- grounding.py
- refusal.py
- runner.py
- types.py
- __init__.py
- analytic_judge.py
- atomic_claims.py
- checkpoint.py
- embedding_classifier.py
- errors.py
- manifest.py
- normalizer.py
- pipeline.py
- proportion_ci.py
- response_classifier.py
- schemas.py
- types.py
- __init__.py
- ci_check.py
- custom_fixture.py
- run_all.py
- run_single.py
- fixture.yaml
- README.md
- acme_legal.yaml
- customer_support.yaml
- healthcare.yaml
- helio_finance.yaml
- hermes_strict.yaml
- nimbusforge_it_infra.yaml
- openclaw_consolidated.yaml
- openclaw_moderate.yaml
- openclaw_strict.yaml
- openwebui.yaml
- software_engineering.yaml
- mock.yaml
- README.md
- schema.json
- smoke_tiny.yaml
- __init__.py
- adversarial_mutator.py
- adversarial_rotator.py
- base.py
- consistency.py
- injection_corpus.py
- prompt_pool.py
- registry.py
- seed_resolver.py
- suites.py
- synonyms.yaml
- validator.py
- version_enforcement.py
- definition.yaml
- runner.py
- definition.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- service.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- schemas.py
- corpus.yaml
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- corpus.yaml
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- prompts.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- rubric_comply.yaml
- rubric_step1.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- rubric_step1.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- schemas.py
- definition.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- classifier.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- corpus.yaml
- definition.yaml
- references.yaml
- rubric.yaml
- rubric_comply.yaml
- runner.py
- definition.yaml
- prompts.yaml
- references.yaml
- rubric.yaml
- runner.py
- corpus.yaml
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- on_topic_prompts.yaml
- prompts.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- runner.py
- definition.yaml
- runner.py
- definition.yaml
- runner.py
- definition.yaml
- runner.py
- definition.yaml
- runner.py
- definition.yaml
- diagnostics.py
- probes.py
- runner.py
- definition.yaml
- diagnostics.py
- probes.py
- runner.py
- definition.yaml
- runner.py
- definition.yaml
- runner.py
- corpus.yaml
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- corpus.yaml
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- corpus.yaml
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- corpus.yaml
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- corpus.yaml
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- corpus.yaml
- definition.yaml
- references.yaml
- rubric.yaml
- runner.py
- definition.yaml
- runner.py
- definition.yaml
- runner.py
- __init__.py
- holdout_ids.py
- policy_grounding.py
- user_selection.py
- __init__.py
- config.py
- evaluator.py
- fallbacks.py
- judge_fallbacks.json
- __init__.py
- eu_ai_act.yaml
- iso_42001.yaml
- loader.py
- nist_ai_rmf.yaml
- owasp_llm_top10.yaml
- __init__.py
- logging.py
- __init__.py
- anthropic.py
- atlascloud.py
- azure.py
- base.py
- bedrock.py
- bridge.py
- gemini.py
- governance_fixture.py
- governance_mixin.py
- http.py
- huggingface.py
- langchain.py
- litellm.py
- minimax.py
- mock_governance.py
- openai.py
- openrouter.py
- resolver.py
- schemas.py
- secrets.py
- __init__.py
- artifact.py
- comparison.py
- gap_analysis.py
- grading.py
- health.py
- regulatory.py
- scorecard.py
- __init__.py
- loader.py
- playbook.md
- __init__.py
- corpus.schema.json
- definition.schema.json
- references.schema.json
- rubric.schema.json
- __init__.py
- category_weights.py
- engine.py
- mandatory_minimums.py
- schemas.py
- __init__.py
- authorized_scope.py
- evidence.py
- holdout.py
- seeds.py
- __init__.py
- fixture_digest.py
- rubric_digest.py
- template_renderer.py
- __init__.py
- _version.py
- api.py
- py.typed
- quick_build.py
- telemetry.py
- wizard.py
- plugin.json
- plugin.json
- bootstrap.ps1
- bootstrap.py
- bootstrap.sh
- hooks.json
- SKILL.md
- example-scorecard.html
- README.md
- requirements.txt
- plot_traction.py
- update_pypi_stats.py
- .gitattributes
- .gitignore
- .pre-commit-config.yaml
- conftest.py
- CONTRIBUTING.md
- count_fixture_fields.py
- LICENSE
- pyproject.toml
- README.ja.md
- README.ko.md
- README.md
- README.zh-CN.md
- SECURITY.md
# Installation Guide
git clone https://github.com/ifixai-ai/iFixAi
Downloads the entire project code from GitHub to your computer.
cd iFixAi
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- Python 3 Python is required to use pip.
pip install "ifixai[openai]" # or anthropic, gemini, etc.: install the provider extra you'll test
Installs the package published on PyPI directly โ no need to clone the source.
pip install "ifixai[anthropic]"
Installs the package published on PyPI directly โ no need to clone the source.
pip install "ifixai[anthropic,openai]" # SUT's + judge's SDKs (or ifixai[all])
Installs the package published on PyPI directly โ no need to clone the source.
Pulled directly from this repo's README.
3. Python
Easypip install "ifixai[openai]" # or anthropic, gemini, etc.: install the provider extra you'll test
Installs the package published on PyPI directly โ no need to clone the source.
pip install "ifixai[anthropic]"
Installs the package published on PyPI directly โ no need to clone the source.
pip install "ifixai[anthropic,openai]" # SUT's + judge's SDKs (or ifixai[all])
Installs the package published on PyPI directly โ no need to clone the source.
Pulled directly from this repo's README.
