# rashadphz/farfalle

🔍 AI search engine - self-host with local or cloud LLMs

Repository: https://github.com/rashadphz/farfalle
Canonical: https://ross.abutalabs.com/products/farfalle
Homepage: https://www.farfalle.dev/
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: fastapi, nextjs, perplexity, react, shadcn-ui, tailwindcss, gpt-4o, groq, openai, generative-ui, ollama, llm, search-engine
Last push: 2024-09-27T07:52:45+00:00

## Health v2 (maintenance only)
Score: 24/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 61
- inputs: {"age_days": 860, "days_push": 705, "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 3541, forks 319 (observed 2026-08-28T04:08:09.185226+00:00)

## What it is
Farfalle is an open-source, self-hosted AI-powered search engine that works like Perplexity, answering questions with cited web search results. It supports local LLMs via Ollama, custom models through LiteLLM, and cloud models from OpenAI and Groq, with multiple search providers including SearXNG, Tavily, Serper, and Bing.

## Use cases
- self-host a Perplexity-style AI search engine
- answer questions with web search results using a local LLM
- run an AI search app with Ollama and llama3 or mistral
- build a private AI search without sending data to cloud providers
- compare search-augmented LLM answers across OpenAI, Groq, and local models
- deploy an AI answer engine with Docker

## When to choose
- you want a self-hosted Perplexity alternative with full control over LLM and search providers
- you want to run AI search entirely locally with Ollama and SearXNG
- you need a Docker-deployable AI answer engine with chat history and expert search

## When to avoid
- you need a managed hosted search API rather than a full web application
- you want a simple library to embed AI search into an existing app
- you need production-grade enterprise search with fine-grained access controls

## Facets
- artifact type: application
- maturity: active
- function: search-engine, llm-inference, rag, chatbot, web-framework, rate-limiting, agent-framework
- domain: artificial-intelligence, large-language-models, self-hosted, web-development
- platform: self-hosted, python, cross-platform
- tags: perplexity-clone, ai-search, ollama, litellm, searxng, fastapi, nextjs, generative-ui, groq, openai, search, natural-language-processing, docker, web-server, nodejs

## Member repositories
- rashadphz/farfalle (main) score 24

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:09.185226+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 2026-08-29T18:34:29.700237+00:00, confidence not recorded.
  - readme: https://github.com/rashadphz/farfalle (fetched 2026-08-28T04:08:09.185226+00:00, sha d77dd81d8d8f)
  - homepage: https://www.farfalle.dev/ (fetched 2026-08-29T09:29:04.427046+00:00, sha 59bb447b000a)
- Data as of 2026-08-30T08:39:29.467469+00:00.