# supermemoryai/opensearch-ai

SearchGPT / Perplexity clone, but personalised for you.

Repository: https://github.com/supermemoryai/opensearch-ai
Canonical: https://ross.abutalabs.com/products/opensearch-ai
Homepage: https://opensearch.supermemory.ai
Language: TypeScript
License Family: other
Last push: 2025-07-08T07:24:20+00:00

## Health v2 (maintenance only)
Score: 37/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 30, release rhythm 35, longevity 54
- inputs: {"age_days": 764, "days_push": 421, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1330, forks 198 (observed 2026-08-28T04:04:24.195921+00:00)

## What it is
OpenSearch GPT is a personalised AI search engine web application that learns about users and their interests as they browse the web. It is a Perplexity/SearchGPT-style clone built with Next.js and powered by Supermemory for memory collection and retrieval.

## Use cases
- run a self-hosted personalised AI search engine
- clone of Perplexity or SearchGPT I can deploy myself
- AI search that learns my interests as I browse
- build an AI answer engine with memory of my browsing
- self-hosted alternative to Perplexity

## When to choose
- you want a Perplexity-style AI search you can self-host and customise
- you want search results personalised by your browsing history and interests
- you want a Next.js codebase to build your own AI search product on

## When to avoid
- you need a production search engine with no license clarity - the repo has no license
- you need a mature, enterprise-grade search product
- you want a search engine that does not send data to third-party AI services

## Facets
- artifact type: application
- maturity: active
- function: search-engine, rag, chatbot, web-framework, llm-inference
- domain: artificial-intelligence, large-language-models, web-development
- platform: cloud
- tags: ai-search-engine, perplexity-clone, personalized-search, nextjs, supermemory, search, retrieval-augmented-generation, web-server, nodejs, typescript

## Member repositories
- supermemoryai/opensearch-ai (main) score 37

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:24.195921+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:45:33.604060+00:00, confidence not recorded.
  - readme: https://github.com/supermemoryai/opensearch-ai (fetched 2026-08-28T04:04:24.195921+00:00, sha 8788a0565ad1)
  - homepage: https://opensearch.supermemory.ai (fetched 2026-08-29T12:04:58.060108+00:00, sha 744389b14741)
- Data as of 2026-08-30T08:39:29.467469+00:00.