Research & Papers

New Open-Source AI Search Engine Promises Privacy and Control

New Open-Source AI Search Engine Promises Privacy and Control

⚡A free, private alternative to Google could soon be in your hands.

Deep Dive

Project Greenhouse represents our exploration of a simple thesis: We believe that it is possible to build fully open and sovereign models for agentic search with only modest computational resources. As a first milestone, we describe how to build a competitive pointwise decoder-only reranker using a simple two-step recipe comprising pre-training from scratch followed by supervised fine-tuning, starting only from commonly available datasets.

Contrary to the dominant approach in the literature, we do not rely on existing open-weight backbones from third parties, and thus we are fully in control of model training, from end to end. We were able to accomplish the bulk of our experiments using no more than a handful of GPUs.

This report articulates the importance and benefits of our approach, and we share artifacts that enable transparent, independent reproduction of all aspects of model training. Beyond data, code, and configurations that capture our efforts, we also release checkpoints for our family of Gaggle models, demonstrating the feasibility of our approach and providing a first step toward validating our broader thesis.

Key Points
  • Project Greenhouse is building a free, open-source AI search engine that you can run yourself, giving you more privacy and control.
  • It uses AI agents to browse the web and answer questions directly, unlike traditional search engines that just list links.
  • The project is still in early stages and may not be ready for everyday use, but it could eventually challenge Google and Bing.

Why It Matters

This could lead to a more private, customizable search experience, reducing reliance on big tech and giving you control over your data.

📬 Get the top 10 AI stories daily