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](https://github.com/toon-format/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| ### JSON in the prompt (43 tokens) ```json {"users":[ {"id":1,"name":"Ada","role":"admin"}, {"id":2,"name":"Lin","role":"analyst"}, {"id":3,"name":"Grace","role":"viewer"} ]} ``` | ### datoon converts → TOON (24 tokens) ```toon users[3]{id,name,role}: 1,Ada,admin 2,Lin,analyst 3,Grace,viewer ``` ```json {"decision":"convert","reason":"Estimated savings 44.19% (threshold 15.00%)."} ``` |
| ### CSV from a data pipeline (111 tokens as JSON) ```csv id,name,role 1,Ada,admin 2,Lin,analyst 3,Grace,viewer ``` | ### datoon auto-converts → TOON (24 tokens) ```bash datoon data.csv --report-stdout ``` Same result. Zero JSON serialization in your code. |
| ### Non-uniform payload (26 tokens) ```json {"config":{"debug":true},"tags":["a","b"]} ``` | ### datoon skips → keeps JSON ```json {"decision":"skip","reason":"No uniform object arrays found with at least 3 rows."} ``` No Node.js call. No silent corruption. |