CTON: JSON-compatible, token-efficient text format for LLM prompts
Details
- External ID
- 45990228
- Source
- HN
- Company
- —
- Product
- CTON: JSON-compatible, token-efficient text format for LLM prompts
- Website domain
- github.com
- Launched
- Nov. 20, 2025
- Cohort
- —
- Upvotes
- 13
- Upvotes percentile
- 0.5796943231441049
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Enrichment
- Theme
- native desktop apps and utilities
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- token-efficient text format for llm prompts
- Manually corrected
- False
Could you build this?
Yes Designing a lightweight, concise serialization syntax alternative to JSON and writing an encoder/decoder library to save LLM prompt tokens is straightforward language/string manipulation.
Discussion
1 comment analyzed.
Competitors mentioned: TOON
Competitors
Other products that read as similar to this one — 753 launches clear the similarity bar, closest 8 shown.
Attention rank: #306 of 754 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 21 days after the earliest competitor.
- Tokensift, an open-sourced token-efficiency linter for LLM prompts · hn · 2026-08-29 · 6 upvotes · similarity 0.82
- PrePrompt · hn · 2026-04-28 · 23 upvotes · similarity 0.65
- TokenPath · hn · 2026-07-21 · 5 upvotes · similarity 0.63
- Anki-LLM · hn · 2025-11-02 · 60 upvotes · similarity 0.60
- An LLM translator whose source is a single prompt · hn · 2026-05-26 · 5 upvotes · similarity 0.60
- Reducing LLM input tokens by 70% · hn · 2026-05-12 · 56 upvotes · similarity 0.58
- KillSwitch · hn · 2026-09-19 · 10 upvotes · similarity 0.57
- LLM Wiki · hn · 2026-04-06 · 6 upvotes · similarity 0.56
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.