datoon

{"users":[
  {"id":1,"name":"Ada","role":"admin"},
  {"id":2,"name":"Lin","role":"analyst"},
  {"id":3,"name":"Grace","role":"viewer"}
]}

users[3]{id,name,role}:
  1,Ada,admin
  2,Lin,analyst
  3,Grace,viewer

{"decision":"convert","reason":"Estimated savings 44.19% (threshold 15.00%)."}

id,name,role
1,Ada,admin
2,Lin,analyst
3,Grace,viewer

datoon data.csv --report-stdout

{"config":{"debug":true},"tags":["a","b"]}

{"decision":"skip","reason":"No uniform object arrays found with at least 3 rows."}

┌──────────────────────────────────────────────────┐
│  PAYLOAD SAVINGS (auto avg)    ████░░░░░░   28%  │
│  PAYLOAD SAVINGS (agent skill) ████████░░   62%  │
│  DECISION ACCURACY             ██████████  100%  │
│  HARMFUL CONVERSIONS BLOCKED   ██████████  100%  │
└──────────────────────────────────────────────────┘

# core (JSON, CSV, JSONL, XML — no extra deps)
uv add datoon
pip install datoon

# with YAML support
pip install "datoon[yaml]"

# with Excel support
pip install "datoon[excel]"

# with Parquet / ORC / Avro support
pip install "datoon[columnar]"

# with Apple Numbers support
pip install "datoon[numbers]"

# with tiktoken-based token counting
pip install "datoon[tokens]"

# with MCP server
pip install "datoon[mcp]"

# everything
pip install "datoon[all]"

echo '{"users":[{"id":1,"name":"Ada"},{"id":2,"name":"Lin"},{"id":3,"name":"Grace"}]}' | datoon --report-stdout

datoon data.csv --report-stdout

datoon data.jsonl -o output.toon

datoon data.yaml --report-stdout

datoon data.parquet --report ./report.json

datoon --format csv < data.csv --report-stdout

datoon data.json --force --report-stdout

from datoon import convert_json_for_llm, ConversionConfig, DatoonError

config = ConversionConfig(min_savings_ratio=0.15, max_depth=6, min_uniform_rows=3)

try:
    outcome = convert_json_for_llm(raw_json, config)
except DatoonError as exc:
    raise

# outcome.payload_text  — TOON or original JSON
# outcome.report.decision  — "convert" | "skip"
# outcome.report.reason    — human-readable explanation
send_to_model(outcome.payload_text)

import json
from pathlib import Path
from datoon import read_tabular, convert_json_for_llm, ConversionConfig

# text formats: csv, jsonl, yaml, xml
rows = read_tabular("csv", text=csv_string)

# binary formats: excel, parquet, orc, avro, numbers
rows = read_tabular("parquet", path=Path("data.parquet"))

json_text = json.dumps(rows, separators=(",", ":"))
outcome = convert_json_for_llm(json_text, ConversionConfig())
send_to_model(outcome.payload_text)

from datoon.analyzer import analyze_payload
from datoon.models import ConversionConfig

analysis = analyze_payload(parsed_data, ConversionConfig())
print(analysis.is_candidate, analysis.reason)

{
  "mcpServers": {
    "datoon": {
      "command": "uvx",
      "args": ["--from", "datoon[mcp]", "datoon", "mcp"]
    }
  }
}

datoon mcp     # or the standalone script: datoon-mcp

claude plugin marketplace add andrii-su/datoon
claude plugin install datoon@datoon

/datoon
convert this JSON to TOON if it saves tokens
use datoon mode for structured data

PYTHONPATH=src python benchmarks/run.py --dry-run
PYTHONPATH=src python benchmarks/run.py
PYTHONPATH=src python benchmarks/run.py --update-readme

uv sync --extra dev
uvx pre-commit install

pytest -m "not integration"   # unit only (102 tests)
pytest                        # with integration (requires Node.js + npx)

python scripts/validate_skill_sync.py
python scripts/validate_plugin_metadata.py