dweve-ai/hedl

Token-efficient data serialization for LLM/AI. 50% fewer tokens than JSON, 93% better value/token. Rust, schema validation, LSP.

55
/ 100
Established

This helps AI application developers significantly reduce the cost of communicating structured data to Large Language Models (LLMs). It takes your existing JSON, converts it into a token-efficient format, sends it to the LLM, and converts the response back to JSON. AI engineers and developers building LLM-powered applications who are concerned about API costs will find this useful.

Use this if you are sending structured data like user records, product catalogs, or order histories to LLMs and want to cut down on token usage and API costs without changing your application code.

Not ideal if your application does not frequently send structured data to LLMs or if you are not concerned about the token costs associated with LLM interactions.

AI-application-development LLM-cost-optimization API-integration data-serialization AI-engineering
No Package No Dependents
Maintenance 10 / 25
Adoption 12 / 25
Maturity 13 / 25
Community 20 / 25

How are scores calculated?

Stars

65

Forks

30

Language

Rust

License

Apache-2.0

Last pushed

Mar 02, 2026

Monthly downloads

56

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/dweve-ai/hedl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.