ISON
Data format that uses 30-70% fewer tokens than JSON for LLMs
Details
- External ID
- 46397566
- Source
- HN
- Company
- —
- Product
- ISON
- Website domain
- github.com
- Launched
- Dec. 26, 2025
- Cohort
- —
- Upvotes
- 7
- Upvotes percentile
- 0.35877862595419846
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
ISON (Interchange Simple Object Notation) - a data format optimized for LLMs and Agentic AI.The problem: JSON wastes tokens. Curly braces, quotes, colons, commas - all eat into your context window.ISON uses tabular patterns that LLMs already understand from training data:JSON (87 tokens): { "users": [ {"id": 1, "name": "Alice", "email": "[email protected]"}, {"id": 2, "name": "Bob", "email": "[email protected]"} ] }ISON (34 tokens): table.users id:int name:string email 1 Alice [email protected] 2 Bob [email protected]: - 30-70% token reduction - Type annotations - References between tables - Schema validation (ISONantic) - Streaming format (ISONL)Implementations: Python, JavaScript, TypeScript, Rust, C++ 9 packages, 171+ tests passingpip install ison-py # Parser pip install isonantic # Validation & schemasnpm install ison-parser # JavaScript npm install ison-ts # TypeScript with full types npm install isonantic-ts # Validation & schemas[dependencies] ison-rs = "1.0" isonantic-rs = "1.0" # Validation & schemasLooking for feedback on the format design.
Enrichment
- Theme
- niche developer utilities and toolchains
- Vertical
- Horizontal
- Function
- Data infrastructure
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- token-efficient data format for llms
- Manually corrected
- False
Could you build this?
Yes ISON is a text-based serialization format designed to encode JSON-like structures into a compact tabular text syntax, which can be implemented with a basic parser and serializer.
Discussion
14 comments analyzed.
Competitors mentioned: JSON, CSV, msgpack, JSON-COMPACT, TOON
Concerns raised: Loss of nesting and semantic structure compared to JSON, Alternative formats lack training data prevalence - LLMs must translate back to JSON, Token savings offset by translation overhead and confusion, Irrelevant optimization since tokens are getting cheaper, Unclear LLM accuracy benefits over established formats
Feature requests: Publish formal benchmark results comparing formats, Support for syntax highlighting in code fences (ison language tag)
Competitors
Other products that read as similar to this one — 50 launches clear the similarity bar, closest 8 shown.
Attention rank: #28 of 51 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 55 days after the earliest competitor.
- A text format for UI wireframes · hn · 2026-02-05 · 5 upvotes · similarity 0.47
- A new benchmark for testing LLMs for deterministic outputs · hn · 2026-04-29 · 60 upvotes · similarity 0.44
- Robust LLM extractor for websites in TypeScript · hn · 2026-03-26 · 72 upvotes · similarity 0.42
- json-toolkit · github · 2026-09-29 · 43 upvotes · similarity 0.38
- Seam · ph · 2026-09-06 · 2 upvotes · similarity 0.37
- json-kit.nvim · github · 2026-09-22 · 8 upvotes · similarity 0.37
- Myjs An accidental pure-Python JavaScript interpreter · hn · 2026-09-05 · 7 upvotes · similarity 0.37
- genpark-json-schema-to-regex-converter-skill · github · 2026-09-29 · 7 upvotes · similarity 0.36
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a data infrastructure tool for Media & entertainment yet.