# mckaywrigley/clarity-ai

A Perplexity clone.

Repository: https://github.com/mckaywrigley/clarity-ai
Canonical: https://ross.abutalabs.com/products/clarity-ai
Homepage: https://JoinTakeoff.com
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2024-03-28T04:13:59+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 92
- inputs: {"age_days": 1291, "days_push": 888, "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 1418, forks 273 (observed 2026-08-28T04:04:40.213625+00:00)

## What it is
Clarity AI is an open-source clone of Perplexity.ai that answers user queries by scraping Google search results, parsing the webpages, and using OpenAI's API to generate and stream an answer. It is a TypeScript web app intended as an educational example of building an AI-powered answer engine.

## Use cases
- build a perplexity clone
- self-host an AI answer engine
- search the web and get an LLM-generated answer
- learn how to combine web scraping with OpenAI API
- stream LLM answers in a web app
- demo a RAG search assistant

## When to choose
- you want a minimal, readable example of a Perplexity-style answer engine
- you want to self-host a simple AI search tool with your own OpenAI key
- you are learning how to build LLM apps that fetch live web data

## When to avoid
- you need a production-grade search engine with rate limits, caching, and source citations
- you want to avoid scraping Google (fragile and against ToS)
- you need follow-up conversations or modern model support out of the box

## Facets
- artifact type: application
- maturity: maintenance
- function: web-scraping, search-engine, llm-inference, rag, chatbot, http-server
- domain: artificial-intelligence, large-language-models, web-development
- platform: cross-platform
- tags: perplexity-clone, openai, answer-engine, nextjs, streaming, demo-app, search, retrieval-augmented-generation, nodejs, web-server

## Member repositories
- mckaywrigley/clarity-ai (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:40.213625+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 2026-08-30T04:37:58.426703+00:00, confidence not recorded.
  - readme: https://github.com/mckaywrigley/clarity-ai (fetched 2026-08-28T04:04:40.213625+00:00, sha 75245fbcc482)
  - homepage: https://JoinTakeoff.com (fetched 2026-08-29T11:50:48.358496+00:00, sha 29e9f961b06f)
  - site_page: https://www.jointakeoff.com/about (fetched 2026-08-29T11:50:48.364260+00:00, sha 2b10fb196859)
  - site_page: https://www.jointakeoff.com/pricing (fetched 2026-08-29T11:50:48.360970+00:00, sha f96920d1f316)
  - site_page: https://www.jointakeoff.com/changelog (fetched 2026-08-29T11:50:48.362745+00:00, sha 018395019c4f)
- Data as of 2026-08-30T08:39:29.467469+00:00.