Unified compression pipeline for LLM inputs: trim irrelevant rows and fields, re-encode the rest in the cheapest lossless format (TOON / JSON / CSV, measured on your tokenizer), and account for every token saved with an audit trail of what was removed. 95% fewer tokens on realistic payloads, 100% needle recall.

0 stars 0 forks 0 watchers Python Apache License 2.0
ai-cost-optimization anthropic cli context-compression developer-tools llm llmlingua observability openai prompt-compression python rag token-cost tokens toon
8 Open Issues Need Help Last updated: Sep 8, 2026

Open Issues Need Help

View All on GitHub
help wanted roadmap area:sdk

Unified compression pipeline for LLM inputs: trim irrelevant rows and fields, re-encode the rest in the cheapest lossless format (TOON / JSON / CSV, measured on your tokenizer), and account for every token saved with an audit trail of what was removed. 95% fewer tokens on realistic payloads, 100% needle recall.

Python
#ai-cost-optimization#anthropic#cli#context-compression#developer-tools#llm#llmlingua#observability#openai#prompt-compression#python#rag#token-cost#tokens#toon
help wanted roadmap area:ledger

Unified compression pipeline for LLM inputs: trim irrelevant rows and fields, re-encode the rest in the cheapest lossless format (TOON / JSON / CSV, measured on your tokenizer), and account for every token saved with an audit trail of what was removed. 95% fewer tokens on realistic payloads, 100% needle recall.

Python
#ai-cost-optimization#anthropic#cli#context-compression#developer-tools#llm#llmlingua#observability#openai#prompt-compression#python#rag#token-cost#tokens#toon
help wanted good first issue roadmap area:encode

Unified compression pipeline for LLM inputs: trim irrelevant rows and fields, re-encode the rest in the cheapest lossless format (TOON / JSON / CSV, measured on your tokenizer), and account for every token saved with an audit trail of what was removed. 95% fewer tokens on realistic payloads, 100% needle recall.

Python
#ai-cost-optimization#anthropic#cli#context-compression#developer-tools#llm#llmlingua#observability#openai#prompt-compression#python#rag#token-cost#tokens#toon
help wanted roadmap area:bench

Unified compression pipeline for LLM inputs: trim irrelevant rows and fields, re-encode the rest in the cheapest lossless format (TOON / JSON / CSV, measured on your tokenizer), and account for every token saved with an audit trail of what was removed. 95% fewer tokens on realistic payloads, 100% needle recall.

Python
#ai-cost-optimization#anthropic#cli#context-compression#developer-tools#llm#llmlingua#observability#openai#prompt-compression#python#rag#token-cost#tokens#toon
help wanted roadmap area:engine

Unified compression pipeline for LLM inputs: trim irrelevant rows and fields, re-encode the rest in the cheapest lossless format (TOON / JSON / CSV, measured on your tokenizer), and account for every token saved with an audit trail of what was removed. 95% fewer tokens on realistic payloads, 100% needle recall.

Python
#ai-cost-optimization#anthropic#cli#context-compression#developer-tools#llm#llmlingua#observability#openai#prompt-compression#python#rag#token-cost#tokens#toon
good first issue roadmap area:sdk

Unified compression pipeline for LLM inputs: trim irrelevant rows and fields, re-encode the rest in the cheapest lossless format (TOON / JSON / CSV, measured on your tokenizer), and account for every token saved with an audit trail of what was removed. 95% fewer tokens on realistic payloads, 100% needle recall.

Python
#ai-cost-optimization#anthropic#cli#context-compression#developer-tools#llm#llmlingua#observability#openai#prompt-compression#python#rag#token-cost#tokens#toon
help wanted roadmap area:proxy

Unified compression pipeline for LLM inputs: trim irrelevant rows and fields, re-encode the rest in the cheapest lossless format (TOON / JSON / CSV, measured on your tokenizer), and account for every token saved with an audit trail of what was removed. 95% fewer tokens on realistic payloads, 100% needle recall.

Python
#ai-cost-optimization#anthropic#cli#context-compression#developer-tools#llm#llmlingua#observability#openai#prompt-compression#python#rag#token-cost#tokens#toon

Unified compression pipeline for LLM inputs: trim irrelevant rows and fields, re-encode the rest in the cheapest lossless format (TOON / JSON / CSV, measured on your tokenizer), and account for every token saved with an audit trail of what was removed. 95% fewer tokens on realistic payloads, 100% needle recall.

Python
#ai-cost-optimization#anthropic#cli#context-compression#developer-tools#llm#llmlingua#observability#openai#prompt-compression#python#rag#token-cost#tokens#toon