oramasearch/orama
🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.
Implements BM25 ranking, typo tolerance, and multilingual stemming across 30 languages with pluggable embedding generation via TensorFlow.js. Built on a schema-driven architecture supporting nested objects and multiple data types including geopoints, with a plugin system for extensibility. Targets browser, Node.js, Deno, and edge runtimes through universal JavaScript with optional server-side persistence and a cloud-hosted answer engine for RAG workflows.
10,221 stars.
Stars
10,221
Forks
378
Language
TypeScript
License
—
Category
Last pushed
Feb 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/oramasearch/orama"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
meilisearch/meilisearch
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
nuclia/nucliadb
NucliaDB, The AI Search database for RAG
vespa-engine/vespa
AI + Data, online. https://vespa.ai
PrithivirajDamodaran/FlashRank
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and...
ICIJ/datashare
A self‑hosted search engine for documents