# ammaarreshi/Gemini-Search

Perplexity style AI Search engine clone built with Gemini 2.0 Flash and Grounding

Repository: https://github.com/ammaarreshi/Gemini-Search
Canonical: https://ross.abutalabs.com/products/gemini-search
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2025-01-04T14:37:03+00:00

## Health v2 (maintenance only)
Score: 21/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 43
- inputs: {"age_days": 606, "days_push": 606, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2068, forks 411 (observed 2026-08-28T04:06:10.229625+00:00)

## What it is
A Perplexity-style AI search engine web application powered by Google's Gemini 2.0 Flash model with Google Search grounding. It provides AI-generated answers with real-time web sources, citations, and follow-up chat in a modern React UI.

## Use cases
- build a perplexity-style ai search engine
- get ai answers with web citations
- clone ai search with gemini
- search the web with an llm and see sources
- ask follow-up questions with grounded search
- self-host an ai answer engine

## When to choose
- you want a self-hosted Perplexity alternative using Gemini 2.0 Flash
- you need a reference implementation of Gemini grounding with Google Search
- you want a clean React + Express starter for AI search apps

## When to avoid
- you need a production-grade search service with auth, scaling, and rate limiting
- you don't have a Google API key with Gemini access
- you need search grounded in sources other than Google Search

## Facets
- artifact type: application
- maturity: active
- function: search-engine, chatbot, web-framework, llm-inference, rag
- domain: artificial-intelligence, large-language-models, web-development
- platform: cross-platform
- tags: perplexity-clone, gemini, grounding, ai-search, citations, react, express, typescript, search, natural-language-processing, nodejs, web-server

## Member repositories
- ammaarreshi/Gemini-Search (main) score 21

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.229625+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 2026-08-30T02:56:47.078602+00:00, confidence not recorded.
  - readme: https://github.com/ammaarreshi/Gemini-Search (fetched 2026-08-28T04:06:10.229625+00:00, sha 1e14652d6d94)
- Data as of 2026-08-30T08:39:29.467469+00:00.