Skip to Content

SDKs

Official SDKs for implementing the AI Provenance Protocol in your applications.

Status

SDKs are currently in development. The specification is stable enough for implementations — the SDKs will provide convenience wrappers.

SDKLanguagePackageStatus
@ai-provenance-protocol/sdkTypeScriptnpmComing soon
ai-provenance-protocolPythonPyPIComing soon

SDK design

The SDKs will provide four core functions:

Create metadata

import { APP } from '@ai-provenance-protocol/sdk' const metadata = APP.create({ generator: { platform: 'my-platform', model: 'anthropic/claude-sonnet-4', }, })

Embed in output

const output = APP.embed(generatedContent, metadata) // { ...generatedContent, _ai_provenance: metadata }

Extract from output

const { content, app } = APP.extract(outputWithMetadata)

Validate metadata

const result = APP.validate(metadata) // { valid: true } or { valid: false, errors: [...] }

Record human review

const reviewed = APP.review(metadata, { reviewer_role: 'editor', review_type: 'approved_without_changes', })

Verify remotely

const verification = await APP.verify( metadata.generation_id, metadata.verification_uri )

Implementing without an SDK

You don’t need an SDK to implement APP. The protocol is simple enough to implement directly:

  1. Generate a UUID v4 for generation_id
  2. Construct the metadata JSON object
  3. Embed using your chosen embedding mode
  4. Validate against the JSON Schema 

Contributing

Interested in building an SDK for another language? See the Contributing Guide .

Last updated on