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
| Stars | 312 |
| Forks | 2 |
| Language | Python |
| Category | AI Tool |
| License | MIT |
| Quality Score | 64.4367355470561/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-28 |
| Created | 2026-04-18 |
| Platforms | gemini, python |
| Est. Tokens | ~16k |
Explore other popular ai tool tools:
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.
leanctx is primarily written in Python. It covers topics such as anthropic, cost-optimization, gemini.
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.
leanctx is released under the MIT license, making it free to use and modify according to the license terms.