Skip to main content

ai-evidence (Python)

Python implementation of the AI Evidence Manifest — a static /ai.json file that links the claims a site makes to the first-party evidence supporting them.

pip install ai-evidence
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:

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 — specification, schema and both reference implementations alike.

Release files for ai-evidence 0.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ai-evidence 0.3.0
File Size Uploaded
ai_evidence-0.3.0.tar.gz 47.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for ai-evidence 0.3.0
File Interpreter ABI Platform
ai_evidence-0.3.0-py3-none-any.whl Python 3 none any Details

Total release size: 97.3 kB

Release files / ai_evidence-0.3.0.tar.gz

Download URL ai_evidence-0.3.0.tar.gz
Size 47.7 kB
Tags Source
SHA-256 checksum
How to use checksums
9283cb5e1378774168083b9af3b6003d0aec6188c17883335ee7990acbe940df
BLAKE2b-256 checksum
How to use checksums
f376741881d1c373735269f231fb83ae4c606262d0761e44d347386293b1ccbc
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.14

Release files / ai_evidence-0.3.0-py3-none-any.whl

Download URL ai_evidence-0.3.0-py3-none-any.whl
Size 49.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e3467d517fc2b7db6b7d03533374b9eaebd5c63dbb0338fef35ff9c5339f5b45
BLAKE2b-256 checksum
How to use checksums
133bf1baa24e9227d3f82a1df5f63896a2083e608a6a567fbb28b4f59593e274
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.14

Release history Release notifications | RSS feed

This release

0.3.0 This release

2 release files

0.2.0

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page