← Directory

Perplexica

Perplexica is an open-source, privacy-focused AI answering engine that runs entirely on your own hardware - an open alternative to Perplexity AI.

  • AI
Perplexica is an open-source, privacy-focused AI answering engine that runs entirely on your own hardware - an open alternative to Perplexity AI. The project has since been rebranded to "Vane" by its maintainer, but the Docker image and functionality remain the same. It combines web search results with local LLMs (via Ollama) or cloud AI providers (OpenAI, Anthropic Claude, Google Gemini, Groq, and more) to deliver accurate, cited answers while keeping your searches completely private. This template uses the all-in-one image which bundles SearxNG directly inside the container, so no separate SearxNG container or additional setup is required. Simply start the container, open the Web UI, and configure your AI provider (API keys, models, etc.) in the setup screen. If you already run a separate SearxNG instance, use the "itzcrazykns1337/vane:slim-latest" image instead and set a

Platform availability

Available on 2 of 9 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

70/100 Good

Maintained
71last commit 42 days ago
Popular
9137,147 GitHub stars
Easy to install
602 install platforms, install notes, setup guide, Docker image
Light to run
208 GB minimum RAM, runs on ARM
Security check
90no serious findings, CI

Availability: platform listings confirmed today, links checked 7 days ago

GitHub stars
37,147
Open issues
356
Last commit
2026-09-01
Latest release
v1.12.2
License
MIT
Activity
stale

Checked 5 days ago - source: GitHub (ItzCrazyKns/Perplexica)

Resources & Compatibility

Minimum requirements: 8 GB RAM. ARM (e.g. Raspberry Pi) is supported.

Checked 14 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Set required settings before starting Add DATA_DIR, SEARXNG_API_URL, and OPENAI_API_KEY before starting. Without these, the app can save nothing, find no web search results, or get no AI answers. source
  • Use a data folder you can back up Set DATA_DIR to a folder you keep and back up, and for Docker mount it as a volume. If this folder is lost, your settings and saved files disappear. source
  • Set the SearXNG address correctly SEARXNG_API_URL is the setting that points to your web search server. If SearXNG is in another Docker container, use its container name, like http://searxng:4000, not localhost; otherwise searches fail. source

Fetched 14 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Does the Docker setup require a separate SearxNG container?

No. The guide describes one Docker image with SearXNG bundled, so you can start Perplexica without running another SearxNG service.

Where should DATA_DIR point?

Point DATA_DIR to a folder you keep and back up, and mount it as a Docker volume. If that folder is lost, settings and saved files disappear.

How should I configure SearXNG when it runs in another Docker container?

Set SEARXNG_API_URL to the SearXNG container name, not localhost. This prevents searches from failing because of an unreachable address.

Can I use a local model instead of a hosted AI API?

Yes. It supports local LLMs through Ollama as well as cloud providers such as OpenAI, Claude, Groq, and Google Gemini.

Answers sourced from deepwiki.com, github.com, joshuaopolko.com

Community

Collected 13 days ago - public community threads

Install guides