Ross ROSS = Recommend OSS · open-source software intelligence for agents

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. observed · 2026-08-28

github.com/oramasearch/orama · homepage · TypeScript · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

84/100

  • Activity 95
  • Release rhythm 62
  • Longevity 100

Flags: no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 8
  • age_days: 1576
  • days_rel: 257
  • days_push: 30
  • n_releases_24m: 34

Full methodology

Adoption not part of the score

10533 stars · 399 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Orama is a lightweight (~2kb) search engine and RAG pipeline library written in TypeScript that runs in the browser, server, or edge network. It supports full-text, vector, and hybrid search with features like typo tolerance, BM25 scoring, facets, geosearch, and multilingual stemming.

Use cases

  • add full-text search to a javascript app
  • run a vector search database in the browser
  • build a hybrid search engine with keyword and semantic matching
  • create a RAG answer engine over my documents
  • implement typo-tolerant search for a small dataset
  • add faceted search and filters to an e-commerce site
  • search documents on edge/serverless functions without a database server
  • support stemming and tokenization in multiple languages

When to choose

  • you need embedded search with no external service or server dependency
  • you want full-text, vector, and hybrid search in one tiny library
  • you're building for browser, edge, or serverless environments where footprint matters
  • you need a lightweight RAG/answer-engine pipeline in JavaScript or TypeScript

When to avoid

  • you need a large-scale distributed search cluster like Elasticsearch or OpenSearch
  • you require heavy-duty persistence, replication, or multi-node indexing
  • your dataset is too large to hold in memory
  • you need a managed hosted search service with dashboards and analytics

Facets

library · maturity active

search-engine vector-database rag plugin-system nlp databases web-development browser bun cross-platform cli full-text-search hybrid-search typo-tolerance bm25 geosearch embeddings answer-engine edge-runtime facets stemming search retrieval-augmented-generation natural-language-processing nodejs deno web-server

7 sources

Member repositories

RepositoryRoleHealth v2
oramasearch/oramamain84

For agents

markdown · JSON · MCP: product_card(name="oramasearch/orama")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem