Metadata-Version: 2.5
Name: ai-evidence
Version: 0.3.0
Summary: Reference tooling for the AI Evidence Manifest: a static /ai.json file linking website claims to the first-party evidence supporting them.
Project-URL: Homepage, https://github.com/DominionLabsInc/ai-evidence-manifest
Project-URL: Specification, https://github.com/DominionLabsInc/ai-evidence-manifest/blob/main/SPEC.md
Project-URL: Issues, https://github.com/DominionLabsInc/ai-evidence-manifest/issues
Author-email: "Dominion Labs, Inc." <info@dmnlabs.org>
License-Expression: Apache-2.0
License-File: LICENSE
License-File: NOTICE
Keywords: agents,ai,evidence,json-schema,manifest,provenance
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Internet :: WWW/HTTP
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.9
Requires-Dist: cryptography>=42
Requires-Dist: html5lib>=1.1
Requires-Dist: jsonschema[format]>=4.0
Provides-Extra: dev
Requires-Dist: pytest>=7; extra == 'dev'
Description-Content-Type: text/markdown

# ai-evidence (Python)

Python implementation of the [AI Evidence Manifest](https://github.com/DominionLabsInc/ai-evidence-manifest) —
a static `/ai.json` file that links the claims a site makes to the first-party
evidence supporting them.

```bash
pip install ai-evidence
```

```bash
ai-evidence init https://example.com   # write ai-evidence.config.json
ai-evidence generate                   # read the site, write ai.json
ai-evidence check ai.json --update     # re-verify, record freshness
ai-evidence repair ai.json             # relocate quotes that have drifted
```

As a library:

```python
from ai_evidence import validate_manifest, parse_manifest

manifest, size = parse_manifest(open("ai.json").read())
result = validate_manifest(manifest, offline=False)

print(result["valid"], result["stats"])
```

## Parity with the JavaScript implementation

Both implementations load the same `shared/patterns.json` and validate against
the same JSON Schema, and a conformance corpus checks that they produce
identical output for identical input. Where the two regex engines differ — the
spelling of Unicode character classes — the shared file uses placeholders that
each language substitutes.

## Licence

[Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) — specification,
schema and both reference implementations alike.
