Devtoolwatch BoardOrama review
Orama is a TypeScript search engine and RAG pipeline for browser, server, or edge, supporting full-text, vector, and hybrid search.
TL;DR
Orama is a search engine and RAG pipeline that runs in the browser, on a server, or on an edge network. It is for JavaScript and TypeScript developers who want in-app full-text, vector, or hybrid search. Orama also offers chat-style answer sessions and a plugin system.
- 10.6kGitHub stars
- +10new stars, week of Oct 25
- ~2.3Mdownloads a week, +36% vs 4-week avg
- #20in RAG, data and memory this week
Orama at a glance
- Category
- RAG, data and memory
- Maintained by
- Orama (organization, @oramasearch on GitHub)
- Language
- TypeScript, Astro, MDX
- Repository
- github.com/oramasearch/orama
- Website
- docs.orama.com/docs/orama-js
- npm package
- @orama/orama 3.1.18
- Latest release
- v3.1.18 on GitHub, Dec 19, 2025
- First published
- May 10, 2022
What Orama does
- Orama runs full-text, vector, and hybrid search, selected with a mode option of 'fulltext', 'vector', or 'hybrid'.
- Orama supports search filters, facets, geosearch, fields boosting, typo tolerance, exact match, and BM25 ranking.
- Orama provides stemming and tokenization in 30 languages.
- Orama offers GenAI chat sessions through AnswerSession, which builds ChatGPT- or Perplexity-like experiences since v3.0.0.
- Orama supports pinning rules for merchandising, letting you pin documents in results.
- Orama can generate embeddings at insert and search time with the @orama/plugin-embeddings plugin.
- Orama has official plugins for analytics, data persistence, Vitepress, Docusaurus, Astro, and Nextra.
How it works
You import Orama as a JavaScript library, create a database with a typed schema, insert documents, and call search. Schemas support ten data types, including geopoint and vector[size]. Vector search needs embeddings, either supplied by you or generated by the embeddings plugin with a TensorflowJS backend. Chat features call OpenAI APIs, ideally through the Secure Proxy plugin.
How to install and start using Orama
With npm
npm i @orama/oramaRequirements
- Node.js 20.0.0 or later.
- An OpenAI API key for chat and OpenAI embedding features, routed through the Secure Proxy plugin.
- A TensorflowJS backend, such as @tensorflow/tfjs-node, when using @orama/plugin-embeddings.
First steps
- Install the package, then import create, insert, and search from '@orama/orama'.
- Create a database with a schema; declare vector sizes, such as 'vector[1536]', when you define the schema.
- Insert documents with insert or insertMultiple.
- Call search with a term, or set mode to 'vector' or 'hybrid' and pass embeddings.
Who Orama is for
- JavaScript or TypeScript apps that need search running in the browser, server, or edge.
- Documentation sites built with Vitepress, Docusaurus, Astro, or Nextra.
- E-commerce search needing facets, filters, and result pinning.
- Developers building client-side RAG or chat answer experiences.
Limitations to know
- Orama requires you to fix vector dimensions when you initialize the schema.
- Orama's embeddings plugin generates 512-dimension vectors, so the schema property must be vector[512].
- Orama's built-in chat example relies on OpenAI models, which requires an external API.
- Orama returning embeddings with includeVectors can produce very large responses.
Is Orama growing? Usage data
In the week of Oct 25–31, 2026, Orama ranked #197 on the Devtoolwatch Board and #20 in RAG, data and memory, with a momentum score of 45 out of 100. Its main package had about 2.3M downloads that week, +36% against its own 4-week average.
Show the weekly numbers
| Week of | New stars |
|---|---|
| Aug 9, 2026 | 14 |
| Aug 16, 2026 | 8 |
| Aug 23, 2026 | 13 |
| Aug 30, 2026 | 14 |
| Sep 6, 2026 | 3 |
| Sep 13, 2026 | 9 |
| Sep 20, 2026 | 10 |
| Sep 27, 2026 | 7 |
| Oct 4, 2026 | 12 |
| Oct 11, 2026 | 8 |
| Oct 18, 2026 | 7 |
| Oct 25, 2026 | 10 |
The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.
Orama alternatives
Other RAG, data and memory tools on the Board in the week of Oct 25–31, 2026, by momentum:
| Rank | Tool | Stars | Downloads/wk |
|---|---|---|---|
| #1 | XERJXERJ is a local-first search engine and MCP server for AI agents, packaged as one Rust binary with an Elasticsearch-compatible API. | 17.9k | – |
| #2 | MemvidMemvid is a single-file memory layer for AI agents that packages data, embeddings, search indexes, and metadata into one portable .mv2 file. | 17.3k | – |
| #3 | LEANNLEANN is a Python vector database and RAG library that recomputes embeddings on demand to keep indexes small on personal devices. | 13.7k | – |
| #4 | GraphifyGraphify is an AI coding assistant skill that turns a codebase, with its docs, PDFs, images and videos, into a queryable knowledge graph. | 140k | 480.7k |
| #5 | MarkItDownMarkItDown is a lightweight Python utility from Microsoft that converts PDFs, Office documents, images, audio and other files to… | 193.2k | 4.7M |
| #6 | FirecrawlFirecrawl is an API and open source project to search, scrape, crawl, and interact with web pages, returning LLM-ready markdown or JSON… | 197.4k | 2.9M |
Recent Orama releases
Orama FAQ
Is Orama free and open source?
Orama's code is on GitHub (oramasearch/orama), but the repository doesn't declare a standard open-source license. Check its license file before using it commercially.
How do I install Orama?
Run npm i @orama/orama. It needs Node.js >= 20.0.0. The install section above has the other options from the project's README.
Is Orama still maintained?
Yes. The oramasearch/orama repository was last updated on Oct 18, 2026, and the latest release, v3.1.18 on GitHub, came out on Dec 19, 2025.
How popular is Orama?
Orama has 10.6k GitHub stars as of Nov 1, 2026. It gained 10 new stars in the week of Oct 25–31, 2026, against a 12-week average of 10 a week. Its main package had about 2.3M downloads that week, +36% against its own 4-week average. That made it #20 among RAG, data and memory tools on the Devtoolwatch Board.
What are the best alternatives to Orama?
Other RAG, data and memory tools on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: XERJ (#1), Memvid (#2), LEANN (#3), Graphify (#4), MarkItDown (#5). The alternatives table above has their numbers.
What does Orama do?
Orama is a search engine and RAG pipeline for the browser, server, or edge network. Orama supports full-text, vector, and hybrid search, plus filters, facets, geosearch, and chat answer sessions.
Does Orama generate embeddings?
Orama can generate embeddings with the @orama/plugin-embeddings plugin. The plugin creates 512-dimension vectors at insert time and at search time in vector or hybrid mode. It needs a TensorflowJS backend.
Can Orama run in Deno or directly in a browser?
Orama runs in both. You can import Orama in a browser module from the jsDelivr CDN. In Deno, use the same CDN URL or the npm specifier 'npm:@orama/orama'.
How does Orama handle RAG and chat?
Orama has provided AnswerSession for chat-style answers since v3.0.0. The session calls OpenAI models, and the README recommends the Secure Proxy plugin for calling them safely from the client side.
Can Orama persist its index?
Orama offers an official Data Persistence plugin. Release v3.1.13 added a seqproto serialization format for disk persistence.
Sources
Orama README badge
Maintainers can show the tool's weekly Board rank in their README:
[](https://index.devtoolwatch.com/tools/oramasearch-orama/)How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].