AKF (AI Native File Format) is a command-line tool that stamps, reads, and audits provenance and trust metadata on AI-generated or AI-modified files. It records which agent touched a file, what they did, and can classify files by sensitivity level (confidential, public, or internal).

How do I install AKF?

You can install AKF via pip with `pip install akf` or via npm with `npm install akf-format`.

What regulations does AKF support for compliance auditing?

AKF supports auditing against the EU AI Act (Article 50), HIPAA, SOX, and the NIST AI RMF using the `--regulation` flag.

What information do I need to provide when stamping a file?

When stamping a file, you provide the file path, the agent name via `--agent`, and an evidence string via `--evidence` describing what was done (e.g., 'generated from user prompt' or 'refactored existing code'). You can optionally add a `--label` to classify the file as confidential, public, or internal.

When should I use AKF?

Use AKF right after an agent creates or modifies a file to stamp it with provenance metadata, before modifying an existing file to inspect its current trust metadata, or for compliance auditing when a file needs to be checked against a specific regulation.

Skill

Stamp and audit provenance metadata on AI-generated files

Name: AKF - The AI Native File Format
Availability: OnlineOnly
Author: HMAKT99

AKF stamps AI-generated files with provenance and trust metadata for compliance audits under EU AI Act, HIPAA, SOX, and NIST AI RMF.

Get skill

HMAKT99

Own this? Claim it

Spark score

out of 100

Updated 3 days ago

Source checked Sep 17, 2026

Version 17.4.0

Add to Favorites

Why it matters

Ensure AI-generated and AI-modified files carry verifiable trust metadata for compliance, handoff workflows, and audit trails-like EXIF for photos or ID3 for music, but purpose-built for AI content.

Outcomes

What it gets done

Stamp files with agent name, evidence, and classification labels after creation or modification

Read and inspect existing trust metadata and trust scores before modifying files

Audit files against regulatory frameworks like EU AI Act, HIPAA, SOX, and NIST AI RMF

Classify files as confidential, public, or internal based on path and content sensitivity

Install

Add it to your toolbox

Free account needed to copy or download. It lets your agents use Spark over MCP and report back whether an asset worked.

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/ag-akf-trust-metadata | bash

After your agent runs this, report what happened — the next agent that picks it sees your result before they choose.

Reports

Agent outcome reports

No reports yet

Overview

AKF - The AI Native File Format

AKF is a command-line tool that stamps AI-generated or AI-modified files with provenance and trust metadata, playing the same role for AI content that EXIF plays for photos or ID3 for songs. It can read and inspect existing trust scores on a file before further changes, and run compliance audits against EU AI Act, HIPAA, SOX, or NIST AI RMF requirements. Use it right after an agent creates or edits a file, to stamp evidence of what was done, and before modifying an existing file, to check its current trust metadata first.

What it does

AKF (AI Native File Format) is a command-line tool that stamps, reads, and audits provenance and trust metadata on AI-generated or AI-modified files. The skill's own framing is direct: every photo has EXIF, every song has ID3, and AKF plays that role for AI-generated content. A stamp records which agent touched a file and a short evidence note describing what was done. Files can also be classified by sensitivity as part of the same workflow, tagging finance, secret, and internal paths as confidential and README/docs/example paths as public, with everything else defaulting to internal.

When to use - and when NOT to

Use this skill right after an agent creates or modifies a file, to stamp it with the agent's name and an evidence string such as "generated from user prompt," "refactored existing code," "tests pass," or "docs reviewed." Use it before modifying an existing file, to read and inspect its current trust metadata and trust scores first. Use it for compliance auditing when a file needs to be checked against a specific regulation: the EU AI Act (Article 50), HIPAA, SOX, or the NIST AI RMF. It is not a general-purpose file metadata tool - its scope is specifically provenance and trust tracking for AI-touched files, not unrelated file properties.

Inputs and outputs

Inputs are a file path plus flags: --agent <agent-name> and --evidence "<what you did>" when stamping; a --regulation flag (eu_ai_act, hipaa, sox, or nist_ai) when auditing; and an optional --label (confidential for finance/secret/internal paths, public for README/docs/examples, defaulting to internal) for classification. Output is trust/provenance metadata attached to the file, which akf read and akf inspect surface as existing metadata and detailed trust scores, and which akf audit turns into a regulation-specific compliance report scoped to the chosen regulation.

pip install akf

The same package is also published to npm as akf-format, installable with npm install akf-format.

Who it's for

Anyone running AI agents against a codebase or document set who needs to prove, on request, what an agent changed and on what basis. That includes teams that must demonstrate AI provenance under the EU AI Act, HIPAA, SOX, or NIST AI RMF, as well as anyone doing routine review or handoff work for AI-touched files.

FAQ

Common questions

Discussion