leanctx

by jia-gao · AI Tool · ★ 312

About leanctx

leanctx Drop-in prompt compression for production LLM applications. Cut your input-token bill by 40–60% — without changing your code. On the public LongBench v2 leaderboard's short subset, leanctx-Lingua doubles accuracy versus naive head+tail truncation (40 % vs 20 %) while removing 57 % of tokens. Open-source models, runs locally, MIT-licensed. Your prompts and user data never leave your infrastructure by default. Quickstart (60 seconds) First Lingua call loads 1.2 GB of model weigh

anthropiccost-optimizationgeminilangchainlanggraphllmllm-inferencellmlinguaopenaiprompt-compression

Quick Facts

Stars312
Forks2
LanguagePython
CategoryAI Tool
LicenseMIT
Quality Score64.4367355470561/100
Open Issues1
Last Updated2026-06-28
Created2026-04-18
Platformsgemini, python
Est. Tokens~16k

More AI Tool Tools

Explore other popular ai tool tools:

View all AI Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is leanctx?

leanctx is Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.. It is categorized as a AI Tool with 312 GitHub stars.

What programming language is leanctx written in?

leanctx is primarily written in Python. It covers topics such as anthropic, cost-optimization, gemini.

How do I install or use leanctx?

You can find installation instructions and usage details in the leanctx GitHub repository at github.com/jia-gao/leanctx. The project has 312 stars and 2 forks, indicating an active community.

What license does leanctx use?

leanctx is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse AI Tool tools