batuta 0.1.5

Orchestration framework for converting ANY project (Python, C/C++, Shell) to modern Rust
Documentation

Table of Contents

Overview

Batuta coordinates the Sovereign AI Stack, a comprehensive pure-Rust ecosystem for organizations requiring complete control over their ML infrastructure. The stack enables privacy-preserving inference, model management, and data processing without external cloud dependencies.

Key Capabilities

  • Privacy Tiers: Sovereign (local-only), Private (VPC), Standard (cloud-enabled)
  • Model Security: Ed25519 signatures, ChaCha20-Poly1305 encryption, BLAKE3 content addressing
  • API Compatibility: OpenAI-compatible endpoints for drop-in replacement
  • Observability: Prometheus metrics, distributed tracing, A/B testing
  • Cost Control: Circuit breakers with configurable daily budgets

Installation

cargo install batuta

Or add to your Cargo.toml:

[dependencies]
batuta = "0.1.3"

Quick Start

# Analyze project structure and dependencies
batuta analyze --languages --dependencies --tdg

# Query the Sovereign AI Stack
batuta oracle "How do I serve a Llama model locally?"

# Model registry operations
batuta pacha pull llama3-8b-q4
batuta pacha sign model.gguf --identity alice@example.com
batuta pacha verify model.gguf

# Encrypt models for distribution
batuta pacha encrypt model.gguf --password-env MODEL_KEY
batuta pacha decrypt model.gguf.enc --password-env MODEL_KEY

Stack Components

Batuta orchestrates a layered architecture of pure-Rust components:

┌─────────────────────────────────────────────────────────────┐
│                    batuta v0.1.3                            │
│                 (Orchestration Layer)                       │
├─────────────────────────────────────────────────────────────┤
│     realizar v0.2.2      │         pacha v0.1.1             │
│   (Inference Engine)     │      (Model Registry)            │
├──────────────────────────┴──────────────────────────────────┤
│                    aprender v0.14.1                         │
│               (ML Algorithms & Formats)                     │
├─────────────────────────────────────────────────────────────┤
│                     trueno v0.7.4                           │
│              (SIMD/GPU Compute Primitives)                  │
└─────────────────────────────────────────────────────────────┘

Core Components

Component Version Description
trueno 0.7.4 SIMD/GPU compute primitives with wgpu backend
aprender 0.14.1 ML algorithms: regression, trees, clustering, NAS
pacha 0.1.1 Model registry with signatures, encryption, lineage
realizar 0.2.2 Inference engine for GGUF/SafeTensors models
batuta 0.1.3 Stack orchestration and CLI tooling

Extended Ecosystem

Component Description
trueno-db GPU-accelerated analytics database
trueno-graph Graph database for code analysis
alimentar Data loading with encryption support
renacer Syscall tracing for validation

Commands

batuta analyze

Analyze project structure, languages, and dependencies:

batuta analyze --languages --dependencies --tdg

# Output:
# Primary language: Python
# Dependencies: pip (42 packages), ML frameworks detected
# TDG Score: 73.2/100 (B)
# Recommended: Use Aprender for ML, Realizar for inference

batuta oracle

Query the stack for component recommendations:

# Natural language queries
batuta oracle "Train random forest on 1M samples"

# List all components
batuta oracle --list

# Component details
batuta oracle --show realizar

# Interactive mode
batuta oracle --interactive

batuta pacha

Model registry operations:

# Pull models from registry
batuta pacha pull llama3-8b-q4

# Generate signing keys
batuta pacha keygen --identity alice@example.com

# Sign models for distribution
batuta pacha sign model.gguf --identity alice@example.com

# Verify model signatures
batuta pacha verify model.gguf

# Encrypt models at rest
batuta pacha encrypt model.gguf --password-env MODEL_KEY

# Decrypt for inference
batuta pacha decrypt model.gguf.enc --password-env MODEL_KEY

batuta content

Generate structured content with quality constraints:

# Available content types
batuta content types

# Generate book chapter prompt
batuta content emit --type bch --title "Error Handling" --audience "developers"

# Validate content quality
batuta content validate --type bch chapter.md

Privacy Tiers

The stack enforces data sovereignty through configurable privacy tiers:

Tier Behavior Use Case
Sovereign Blocks ALL external API calls Healthcare, Government
Private VPC/dedicated endpoints only Financial services
Standard Public APIs allowed General deployment 
use batuta::serve::{BackendSelector, PrivacyTier};

let selector = BackendSelector::new()
    .with_privacy(PrivacyTier::Sovereign);

// Returns only local backends: Realizar, Ollama, LlamaCpp
let backends = selector.recommend();

Model Security

Digital Signatures (Ed25519)

Verify model integrity before loading:

use pacha::signing::{SigningKey, sign_model, verify_model};

let signing_key = SigningKey::generate();
let signature = sign_model(&model_data, &signing_key)?;

// Verification fails if model tampered
verify_model(&model_data, &signature)?;

Encryption at Rest (ChaCha20-Poly1305)

Protect models during distribution:

use pacha::crypto::{encrypt_model, decrypt_model};

let encrypted = encrypt_model(&model_data, "password")?;
let decrypted = decrypt_model(&encrypted, "password")?;

Documentation

Design Principles

Batuta applies Toyota Production System principles:

Principle Application
Jidoka Automatic failover with context preservation
Poka-Yoke Privacy tiers prevent data leakage
Heijunka Spillover routing for load leveling
Muda Cost circuit breakers prevent waste
Kaizen Continuous metrics and optimization

Development

# Clone repository
git clone https://github.com/paiml/batuta.git
cd batuta

# Build
cargo build --release

# Run tests
cargo test

# Build documentation
mdbook build book

License

MIT License — see LICENSE for details.

Links

Batuta — Orchestrating sovereign AI infrastructure.