datoon

smart structured-data→TOON gateway — converts only when it actually saves tokens

Before/After • Install • What You Get • How It Works • Benchmarks • Full install guide

Raw structured data is often verbose in LLM prompts. TOON can save tokens — but blind conversion can also make payloads worse. datoon adds a decision layer: convert when structure and savings justify it, skip when they don't, and always explain why.

Supports JSON, CSV, JSONL, YAML, XML, Parquet, Avro, ORC, Excel, and Apple Numbers — auto-detected from file extension.

Before / After

{"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."}

Same data. Right format. Always explained.

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

[!IMPORTANT] datoon saves payload tokens — the structured data portion of your prompt. Token savings depend on payload shape: uniform tabular data converts well; deeply nested or non-uniform structures are skipped. Every decision includes a reason so pipelines can log, debug, and trust the outcome.

Install

# 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]"

Requires Python 3.12+. TOON conversion requires Node.js with npx in PATH — analysis and format reading work without it.

For Claude Code plugin, Codex, and MCP config → INSTALL.md.

What You Get

Supported input formats

How It Works

1. Detect format — from --format flag, file extension, or default to JSON for stdin
2. Read + normalize — parse source into list of row dicts; serialize to compact JSON
3. Analyze structure — uniform object arrays? acceptable depth? minimum rows?
4. Gate early — non-candidates skip before any CLI call; no Node.js overhead
5. Convert + estimate — TOON CLI runs, token savings calculated
6. Gate savings — below threshold → return JSON; above → return TOON with report

Every path returns a ConversionReport with decision, reason, and token estimates. Pipelines never get silent surprises.

Quick Start

JSON (stdin):

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

CSV (auto-detected from extension):

datoon data.csv --report-stdout

JSONL:

datoon data.jsonl -o output.toon

YAML (requires datoon[yaml]):

datoon data.yaml --report-stdout

Parquet (requires datoon[columnar]):

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

Explicit format override:

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

Force conversion (bypass gating — for experiments):

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

Python API

JSON conversion:

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)

Any format via read_tabular:

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)

Structure-only analysis (no Node.js required):

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

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

MCP Server

datoon ships an MCP server with three tools:

Claude Desktop / Cursor / Windsurf config:

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

Run locally:

datoon mcp     # or the standalone script: datoon-mcp

Listed on the MCP Registry, Smithery, and Glama. See MARKETPLACES.md.

Claude Code Plugin

Install directly from GitHub:

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

Trigger in-session:

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

CLI Reference

Format is auto-detected from file extension. Use --format to override or when reading from stdin.

Benchmarks

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

Why auto mode outperforms forced conversion

Auto mode avoids low-benefit and high-risk payloads (orders-nested, mixed-non-uniform) while matching forced TOON's average token count on suitable ones. Every decision comes with a reasoned report.

Forced conversion succeeded for 5/5 payloads.

Format conversion benchmark

Token savings when converting from common structured formats (CSV, JSONL, XML, YAML). Baseline is the JSON representation of the same data — what an LLM would receive without datoon.

Forced conversion succeeded for 4/4 payloads.

Agent skill evaluation

Artifact-based subagent comparison — identical analysis tasks, two modes:

• with_skill: agent received the datoon skill and followed the conversion workflow.
• without_skill: agent used JSON directly, no TOON or datoon.

3 payload sizes × 3 iterations = 18 total agent runs. Both modes: 100% correct answers.

Full report and raw outputs: benchmarks/agent_skill_eval/. Savings are payload-token estimates, not full end-to-end model-token usage.

Development

Contributor workflow: CONTRIBUTING.md. Maintainer/agent notes: CLAUDE.md.

Setup:

uv sync --extra dev
uvx pre-commit install

Tests:

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

Skill sync + plugin metadata:

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

Links

• INSTALL.md — full install matrix, all targets, per-agent detail
• CONTRIBUTING.md — contributor workflow
• CLAUDE.md — maintainer guide for agents
• CHANGELOG.md — release history
• SECURITY.md — vulnerability reporting
• Live docs — docs/
• Issues — bugs, features, questions

License

MIT