usemoss/moss

Moss — is a retrieval layer for production AI systems, providing search under 10ms without vector databases. Works in browser, on edge, on-device, and in cloud, written in Python.

// KEY FEATURES

• Indexes any text data in seconds via its own parser.
• Performs hybrid search (keywords + semantics) in under 10 ms.
• Works offline in the browser and on edge devices without a server.
• Easily integrates into RAG pipelines via a simple Python API.

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.