ZeroEntropy just raised $4.2 million to fix one of AI’s messiest problems: retrieval. The San Francisco startup’s API manages ingestion, indexing, re-ranking, and evaluation to deliver fast, accurate data for AI agents.
The seed round was led by Initialized Capital with input from Y Combinator, Transpose Platform, 22 Ventures, a16z Scout, and angels from OpenAI, Hugging Face, and Front.
ZeroEntropy aims to replace the usual patchwork of vector DBs and keyword search with a streamlined developer tool. CEO Ghita Houir Alami calls it a “Supabase for search,” helping devs deploy reliable retrieval without dumping all data into an LLM’s context window. 
Its proprietary re-ranker, ze-rank-1, claims to outperform Cohere and Salesforce models on public and private benchmarks. Over 10 startups across healthcare, law, sales, and support are already on board.
Houir Alami, a 25-year-old Moroccan-born CEO with degrees from École Polytechnique and UC Berkeley, built an early AI assistant before launching ZeroEntropy. Her goal: better context, better search, fewer errors.
She also pushes for more diversity in AI infra and DevTools, encouraging young women to dive into tough technical challenges.
“Right now, most teams are either stitching together existing tools from the market or dumping their entire knowledge base into an LLM’s context window. The first approach is time-consuming to build and maintain,” Houir Alami said. “The second approach can cause compounding errors. We’re building a developer-first search infrastructure—think of it like a Supabase for search—designed to make deploying accurate, fast retrieval systems easy and efficient.”
“We’ve met a lot of teams building in and around RAG, but Ghita and Nicolas’s models outperform everything we’ve seen,” said Zoe Perret, partner at Initialized Capital. “Retrieval is undeniably a critical unlock in the next frontier of AI, and ZeroEntropy is building it.”
Image Credits: ZeroEntropy
