Perplexica — AI Agent Framework: Live Stats & TrendScore

Perplexica is an open-source Perplexity AI alternative. We track its GitHub star velocity and community discussions around self-hosted search.

GitHub data synced: Apr 11, 2026 • Sentiment updated: Jun 25, 2026

GitHub Statistics

Community Sentiment

Community Buzz: I use Perplexity AI as my new search engine, it is the only one that truly shows you all the sources it use to fetch the information it is showing you, as quoted from HackerNews

Pros & Cons

What People Love

Improved search results, Transparency in source fetching, as praised by HackerNews users

Common Complaints

Copyright theft, Biases in search results

Biggest Positive: AI search improvement

Biggest Negative: Copyright theft

Why Perplexica Stands Out

Vane is different from alternatives because it provides a privacy-focused AI answering engine that runs entirely on your own hardware, allowing for total privacy, model freedom, and zero subscriptions. Its support for local LLMs through Ollama and cloud providers like OpenAI, Claude, and Groq, makes it a unique solution. Vane's ability to deliver accurate answers with cited sources while keeping your searches private is a significant advantage. The project's active development and community feedback also ensure that it is constantly improving.

Built With

Build a self-hosted AI search engine — Vane enables it by providing a privacy-focused answering engine that runs entirely on your own hardware, Build a local LLM model — Vane supports local LLMs through Ollama, Build a custom search engine — Vane allows you to pick your sources and search the web, discussions, or academic papers, Build a smart search interface — Vane provides smart search modes and helpful UI cards, Build a private research agent — Vane keeps your searches completely private and saves your search history locally

Getting Started

  1. Run the command `docker run -d -p 3000:3000 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:latest` to start the Vane container
  2. Open your browser and navigate to http://localhost:3000 to configure your settings
  3. Configure your API keys, models, and other settings directly in the setup screen
  4. Use the command `docker run -d -p 3000:3000 -e SEARXNG_API_URL=http://your-searxng-url:8080 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:slim-latest` to use Vane with your own SearxNG instance
  5. Try searching for a topic to verify that Vane is working correctly

About

Vane is an AI-powered answering engine.

Category & Tags

Category: coding

Tags: ai-agents, ai-search-engine, answering-engine, artificial-intelligence, llm, machine-learning, open-source-ai-search-engine, perplexica, rag, search-engine, searxng, searxng-copilot, self-hosted-ai, vane

Market Context

Competing with Google and other search engines