Originally published on the Sieve blog . Sieve is an open-source (Apache 2.0) context-reduction proxy — I work on it. This is a how-to, not a pitch; the steps work against any Ollama setup. Ollama gives you a local LLM endpoint that is fast, private, and completely stateless. Close the chat, and everything you told the model is gone. Keep the chat open, and every turn re-sends a growing history until the context window fills up. Ask a local model about something it was never told, and — d...