Meilisearch ships AI-powered hybrid search, blending keyword and vector retrieval in one API
techNmak · x · 2026-09-14
Meilisearch (59.3k GitHub stars) is an open-source search engine that lets you build fast application search without stitching together separate keyword and vector systems.
- One API covers typo-tolerant full-text search, semantic and hybrid retrieval, filters, facets and ranking
- A semanticRatio setting controls how much a query leans on keywords vs embeddings, so exact identifiers and vague natural-language queries both work
- Written in Rust, works out of the box for sites and apps
More from coding & agent
- Reviewing 2,000 Lines of Agent Code Isn't Management, It's a New Programming Interface — srchvrs · 2026-09-14
- Hugging Face agents reproduced 2,226 ICML papers — about a third of the conference — mmitchell_ai · 2026-09-14
- GPT-6 Astra in practice: a stubborn genius best used as advisor, not coder — kevinkern · 2026-09-14
- Andrew Chen's homelab for local AI: 5090 eGPU, dual DGX Spark and a routing plugin — andrewchen · 2026-09-14
- One prompt helps uncover obscure bugs in 4 EVM client implementations — banteg · 2026-09-14
- Agency Owner Asks How to Build a Local Agent Stack for Business Ops Beyond Claude Code — icommstudios · 2026-09-14