nooscraft/tokuin
CLI tool – estimates LLM tokens/costs and runs provider-aware load tests for OpenAI, Anthropic, OpenRouter, or custom endpoints.
Built in Rust, it features prompt compression using the Hieratic format—a structured, token-optimized representation achieving 70–90% reduction while remaining natively readable by LLMs. Beyond cost estimation, it provides quality metrics (semantic similarity, instruction preservation, structural integrity) with configurable scoring modes, and supports structured compression for JSON/code/HTML documents plus incremental processing for multi-turn conversations.
128 stars.
Stars
128
Forks
3
Language
Rust
License
—
Category
Last pushed
Feb 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/nooscraft/tokuin"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
connectaman/LoPace
LoPace is a bi-directional encoding framework designed to reduce the storage footprint of...
roli-lpci/lintlang
Static linter for AI agent tool descriptions, system prompts, and configs. Catches vague...
LakshmiN5/promptqc
ESLint for your system prompts — catch contradictions, anti-patterns, injection vulnerabilities,...
sbsaga/toon
TOON — Laravel AI package for compact, human-readable, token-efficient data format with JSON ⇄...
thesupermegabuff/megabuff-cli
🤖 CLI for Better prompts, transparent costs, & zero vendor lock-in. Optimize AI prompts across...