Crate hanzo_ai_format 

Hanzo AI Format - Universal .ai file format for AI artifacts

This crate provides a standard format for packaging, distributing, and sharing AI artifacts across the Hanzo/Zoo network. The .ai format supports:

• Model weights and biases
• Fine-tuning deltas (LoRA, QLoRA)
• Quantized models (GGUF, AWQ, GPTQ)
• Datasets and evaluation data
• Embeddings and vector stores
• Agent state and memory
• Configuration and hyperparameters

File Structure

artifact.ai (ZIP archive with .ai extension)
├── manifest.json          # Artifact metadata and manifest
├── data/                   # Primary artifact data
│   ├── weights/            # Model weights (safetensors, bin, etc.)
│   ├── config/             # Model configuration
│   └── tokenizer/          # Tokenizer files
├── delta/                  # Fine-tuning deltas (optional)
├── dataset/                # Training/eval datasets (optional)
├── embeddings/             # Pre-computed embeddings (optional)
├── state/                  # Agent state/memory (optional)
└── signatures/             # Cryptographic signatures

Storage Backends

The format supports multiple storage backends:

• Local filesystem
• HuggingFace Hub (fallback/mirror)
• P2P swarm (BitTorrent-style distribution)
• IPFS (content-addressed storage)

Example

use hanzo_ai_format::{AiArtifact, ArtifactType, Storage};

// Create a new artifact
let artifact = AiArtifact::builder()
    .name("my-model")
    .artifact_type(ArtifactType::Model)
    .add_weights("weights.safetensors", weights_data)
    .build()?;

// Save to .ai file
artifact.save("my-model.ai").await?;

// Upload to storage
let storage = Storage::new_with_hf_fallback();
storage.upload(&artifact).await?;

Re-exports

pub use artifact::*;

pub use error::*;

pub use manifest::*;

pub use storage::*;

Modules

artifact

AI Artifact - Read/write .ai files

error

Error types for hanzo-ai-format

manifest

Manifest - File listing and metadata for .ai archives

storage

Storage backends for AI artifacts

Structs

ArtifactMetadata

Metadata about the artifact

ArtifactRef

Unique identifier for artifacts

ArtifactStats

Statistics about artifact usage across the network

ComputeRequirements

Compute requirements for using this artifact

Enums

ArtifactType

Type of AI artifact

DatasetTask

Dataset task type

DeltaMethod

Fine-tuning delta method

License

License type for artifacts

Network

Network where artifact is available

QuantFormat

Quantization format

StorageLocation

Storage location for an artifact

Constants

AI_EXTENSION

File extension for AI artifacts

AI_MAGIC

Magic bytes for .ai file format

FORMAT_VERSION

Current format version

Type Aliases

ArtifactId

Artifact identifier (content-addressed)