Home Projects leanctx
leanctx
Python

leanctx

Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.

by jia-gao · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
anthropiccost-optimizationgeminiMITPython
View on GitHub
In plain words

Reduce your input costs by 40-60% when using language models without changing your existing code.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
leanctx — GitHub preview card
📈 Star history
318314
2026-07-202026-08-31
📈 Track leanctx

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.

leanctx has 316 stars on GitHub. It has been forked 3 times. leanctx is written mainly in Python. It has been in active development since 2026. leanctx is available under the MIT license. Its main topics are anthropic, cost-optimization, gemini, langchain.

Frequently asked questions

What is leanctx?

Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.

Is leanctx open source?

leanctx is an open-source project. It is released under the MIT license.

Is leanctx free?

Yes. leanctx is free and open source — you can use, modify and self-host it.

What license does leanctx use?

leanctx is available under the MIT license.

What language is leanctx written in?

leanctx is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — leanctx

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=jia-gao-leanctx)](https://olud.ai/project/jia-gao-leanctx.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.