ZeroEntropy, a San Francisco-based startup founded by Moroccan engineer Ghita Houir Alami and CTO Nicolas Pipitone, has secured $4.2 million in seed funding to enhance AI search infrastructure using retrieval-augmented generation (RAG).
The round was led by Initialized Capital and backed by Y Combinator, a16z Scout, Transpose Platform, and several angels from OpenAI, Hugging Face, and Front.
“Supabase for Search” — Optimizing Context Retrieval
ZeroEntropy provides developers with an API that automates document ingestion, indexing, re-ranking, and retrieval evaluation. Houir Alami describes it as “a Supabase for search,” targeting the backend layer powering generative AI agents. Unlike enterprise-facing tools like Glean, ZeroEntropy is built specifically for developers dealing with complex and messy internal documentation.
The startup’s proprietary re-ranking model, ze-rank-1, is claimed to outperform similar tools from Cohere and Salesforce. It ensures that AI systems fetch the most contextually relevant data, a critical function in areas such as legal tech, HR, healthcare, and customer service.
Advertisement
From Morocco to Silicon Valley
Houir Alami, originally from Morocco, studied at École Polytechnique in France before completing her master’s in mathematics at UC Berkeley. Her journey into machine learning began while exploring conversational agents pre-ChatGPT. That experience led her to realize the need for better retrieval systems to support large language models.
“There aren’t many women in DevTools or AI infra,” she said. “But I’d tell any young woman interested in technical problems: don’t let that stop you.”
ZeroEntropy is already being used by over ten early-stage AI startups and hopes to become a foundational layer for AI search, delivering speed, accuracy, and scalability to developers worldwide.
