Optimized for LLMs & AI

ATON FORMAT V2

Adaptive Token-Oriented Notation

The data serialization format designed for Large Language Models.
Up to 56% token reduction with zero data loss.

Type Safety Native Relationships Smart Defaults Human Readable
56%
Token Reduction vs JSON
4
Compression Modes
$538K
Annual Savings Potential
0%
Data Loss

Core Features

What makes ATON perfect for LLMs and AI applications

56%

Token Reduction

Dramatically lower your LLM API costs. Save thousands on GPT-4, Claude, and other models.

Type Safety

Explicit schema with type definitions. LLMs understand your data structure perfectly.

Human Readable

Easy to read, write, and debug. Both humans and AI can understand it instantly.

Native Relationships

Reference entities directly with → syntax. Perfect for RAG systems and knowledge graphs.

Smart Defaults

Omit repetitive values automatically. @defaults reduces redundancy across records.

Zero Data Loss

Perfect round-trip conversion. decode(encode(data)) === data, always.

NEW IN V2

Production-Grade Enhancements

Enterprise features for large-scale AI deployments

4 Modes

Compression

Fast, Balanced, Ultra, Adaptive - choose your speed/size tradeoff

SQL-like

Query Language

WHERE, SELECT, ORDER BY - filter before encoding

Streaming

Process unlimited data with O(1) memory

100%

Production Ready

Complete error handling, validation, type safety

Real-World Examples

See how ATON transforms complex enterprise data

RAG System with 50 Document Chunks

Retrieval-Augmented Generation system processing 10,000 queries per day with complete metadata.

JSON 3,850 tokens
{
  "documents": [
    {
      "document_id": "doc_2024_001",
      "filename": "Q4_Report.pdf",
      "status": "processed",
      "total_pages": 87,
      "file_size_bytes": 2458624,
      "processing_time_ms": 3450,
      "confidence_score": 0.978,
      "language": "en",
      "document_type": "financial",
      "classification": "confidential",
      "compliance_tags": ["SOX", "GDPR"],
      "embeddings_generated": true,
      "embedding_model": "ada-002"
    }
  ],
  "chunks": [
    {
      "chunk_id": "ch_001",
      "document_id": "doc_2024_001",
      "page_number": 1,
      "content": "Q4 revenue $145.7M...",
      "confidence_score": 0.982,
      "entities": ["revenue", "growth"],
      "created_at": "2024-11-15T09:35:22Z"
    }
    /* ... 49 more chunks */
  ]
}
ATON 1,650 tokens
@schema[doc_id:str, filename:str, pages:int, 
        size:int, process_ms:int, confidence:float]
@defaults[status:"processed", language:"en", 
          embeddings:true, model:"ada-002"]

documents(1):
  doc_2024_001, "Q4_Report.pdf", 87, 2458624,
    3450, 0.978, "financial", "confidential",
    ["SOX","GDPR"]

@schema[chunk_id:str, doc_ref:ref, page:int,
        content:str, confidence:float, 
        entities:arr, created:datetime]

chunks(50):
  ch_001, ->documents[doc_2024_001], 1,
    "Q4 revenue $145.7M...", 0.982,
    ["revenue","growth"],
    2024-11-15T09:35:22Z
  /* ... 49 more rows */
57%
Token Reduction
$660/day
Cost Savings
$237K/year
Annual Savings

Format Comparison

ATON vs JSON, and CSV/VSC

Feature JSON CSV/VSC ATON
Token Efficiency Baseline 71% better 56% better
Type Safety
Nested Support
Relationships ✓ Native
Human Readable
LLM Optimized ✓✓
Schema Flexibility
Default Values

Try It Yourself

Convert your JSON to ATON and see the savings

Conversion Options

Input (JSON)

0 tokens

Output (ATON)

0 tokens

Cost Savings Calculator