Reading the repo
Opening the box…
Reading the repo
Opening the box…
Assembly instructions
Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.
Saved setup from 9 h ago
Will it work on macOS?
Heads-upBuilding it yourself? It also needs 10 settings in .env (3 secret).
pip install 'leanctx[openai,lingua]' # or [anthropic], [gemini]
pip install leanctx # core (passthrough only — useful for testing the wrapper)
pip install 'leanctx[anthropic,openai,gemini]' # provider SDKs
pip install 'leanctx[lingua]' # + LLMLingua-2 local compression (~1.2 GB on first call)
pip install 'leanctx[otel]' # + OpenTelemetry API/SDK
pip install 'leanctx[bench]' # + respx for offline scenarios
pip install 'leanctx[longbench]' # + HuggingFace datasets for LongBench v2
pip install 'leanctx[server]' # + FastAPI/uvicorn HTTP compression sidecar
pip install 'leanctx[all]' # everything
pip install 'leanctx[server,lingua]'
pip install 'leanctx[lingua]'
From the README, exactly as the maintainers wrote it.
No reports for macOS yet.
GitManual AI Agent reads the 8 key files and writes a step-by-step guide for macOS. Once written, it's saved for everyone.