Documentation

Everything you need to get started with Sleev, from initial setup to the full management API.

Getting started

Sleev is a transparent proxy that sits between your coding tool and your LLM provider. It compresses stale context, replays summaries, and strips redundant tokens from every request. You keep using the same models through the same tools; requests are just smaller, and your bill is lower.

Setup takes one config change: point your tool's base URL at Sleev and send the Sleev headers. Your provider credential stays in your local harness or provider config.

Quickstart

Create an account, issue a sleeve token, and configure your coding harness in under five minutes.

API Reference

Full documentation for the current management API: users, sleeve tokens, and usage metadata.

Why Sleev

Learn why context compression matters, how Sleev works with provider caching, and what it is not.

Data Privacy

Understand what the managed cloud service stores and how the local npx package keeps conversation data on your machine.