Content Provenance Python Packages

c2pa

Python implementation of C2PA: Coalition for Content Provenance and Authenticity.

thumbor-ai-label

Visible AI labelling for Thumbor. Reads IPTC/XMP provenance from the original image and marks every derivative - EU AI Act Article 50(4).

vox-trust

Seal real voices, don't chase fakes. Open protocol + Rust/WebAssembly reference: cryptographic voice seals with tamper localization, verifiable offline.

mcp-server-akf

Trust metadata for AI agents — a stamp costs ~15 tokens, re-verifying costs 15,000. Agents stamp what they verify; the next agent runs 'akf check' and builds on it. pip install akf

akf

Trust metadata for AI agents — a stamp costs ~15 tokens, re-verifying costs 15,000. Agents stamp what they verify; the next agent runs 'akf check' and builds on it. pip install akf

langchain-chronoverify

Image provenance for AI agents: drop-in recipes to give any agent capture-time and provenance verification with ChronoVerify. MCP one-click install, OpenAI/Claude tool defs, LangChain/LlamaIndex/CrewAI/n8n, and REST.

ai-provenance-protocol

The AI Provenance Protocol (APP) is an open standard for verifying AI-generated content. It provides a machine-readable format to track model identity, inputs, and human review. Designed for EU AI Act compliance (Article 50) and global governance, APP ensures transparency and accountability for any AI output.

rooted-sbr

Open-source, vendor-neutral C2PA Soft Binding Resolution server on Backblaze B2. Recovers stripped provenance for AI image, audio, and video, with a WORM transparency log and an MCP surface.