Vane
MIT, cited answers from web search through a bundled SearXNG, local models through Ollama or hosted ones, speed, balanced and quality modes, and file uploads.
Know firstNo sign-in yet, and the last tagged release was April 2026.
The open-source alternatives to Perplexity are Vane, formerly Perplexica, Morphic and Khoj. Vane is the closest in shape: ask a question, get an answer with cited sources, with a SearXNG search engine bundled in its Docker image so no search API is needed, and local models through Ollama. Morphic adds a generated page layout, sign-in and shareable results. Khoj answers from your own documents as well as the web and sends scheduled research by email. A team switches to keep its questions private.
3 of 3 carry an OSI licence. 3 of 3 run on your own machines. Figures read from GitHub on September 17, 2026.
One project per need, with the reason from its own README and the one thing to know before you choose it.
MIT, cited answers from web search through a bundled SearXNG, local models through Ollama or hosted ones, speed, balanced and quality modes, and file uploads.
Know firstNo sign-in yet, and the last tagged release was April 2026.
Apache-2.0, cited answers rendered as a generated layout of images, grids and headings, with Tavily, SearXNG, Brave or Exa, Supabase sign-in and shareable results.
Know firstHeavier to run, with PostgreSQL and Redis, and history and sign-in need extra configuration.
AGPL-3.0, any model, semantic search over your PDFs, Markdown, Word and Notion files, custom agents and scheduled research by email.
Know firstIts README does not describe citations or name its search engine.
The facts that decide most choices. Each project's page carries the full panel.
| Project | Best for | Openness | Licence | Runs as | Own machines | Stars |
|---|---|---|---|---|---|---|
| Vane | The closest Perplexity shape, self-hosted | OSI | MIT | Docker, npm | Yes | 36,867 |
| Morphic | A richer answer page with accounts | OSI | Apache-2.0 | Docker Compose, Bun | Yes | 9,125 |
| Khoj | Answers from your documents as well as the web | OSI | AGPL-3.0 | Self-hosted server, Hosted app, Browser, Obsidian, Emacs, desktop, phone and WhatsApp clients | Yes | 37,399 |
Licence and star figures read from GitHub on September 17, 2026. Stars are shown as a dated fact and were not used to rank this page.
An MIT answer engine, formerly Perplexica, that searches the web through a bundled SearXNG and answers with cited sources, using local models through Ollama or hosted ones, in speed, balanced and quality modes, on your own hardware.
MIT, cited answers from web search through a bundled SearXNG, local models through Ollama or hosted ones, speed, balanced and quality modes, and file uploads.
Know firstNo sign-in yet, and the last tagged release was April 2026.
An Apache-2.0 AI search engine with a generative interface that answers with citations, using OpenAI, Anthropic, Google, Ollama or any OpenAI-compatible model and Tavily, SearXNG, Brave or Exa for search, with sign-in and shareable results.
Apache-2.0, cited answers rendered as a generated layout of images, grids and headings, with Tavily, SearXNG, Brave or Exa, Supabase sign-in and shareable results.
Know firstHeavier to run, with PostgreSQL and Redis, and history and sign-in need extra configuration.
An AGPL-3.0 personal AI that answers from the web and your own documents with any local or hosted model, builds custom agents, sends scheduled research by email, and runs self-hosted or in its maintainers' cloud.
AGPL-3.0, any model, semantic search over your PDFs, Markdown, Word and Notion files, custom agents and scheduled research by email.
Know firstIts README does not describe citations or name its search engine.
The questions that settle it, in the order they usually come up.
Khoj. Vane and Morphic answer from the web, with file uploads per search.
Morphic has Supabase sign-in. Vane lists authentication as upcoming.
Vane and Morphic both run SearXNG, so no paid search key is needed.
Perplexity, in the vendor's own words, is a service to "get trusted answers to any question", by Perplexity's own description on its Google Play listing. perplexity.ai. The cases below are where that still wins.
Stars, licence, last commit and last release are read from the GitHub API by a script every week and carry the date they were read. Nobody types them.
What each project does is written from its own README and LICENSE, read in full on the date shown, and phrased as the project's claim. The sources are listed at the end.
That a project is faster, better or cheaper than Perplexity. A price for anyone. A user count. A roadmap. If a fact is not on this page, it was not in the source.
Vane, formerly Perplexica (MIT), is the closest: cited answers, SearXNG bundled so no search API is needed, and local models through Ollama or hosted ones. Morphic (Apache-2.0) adds a richer answer layout, sign-in and shareable links. Khoj (AGPL-3.0) adds your own documents, agents and scheduled research.
It was renamed Vane. GitHub redirects ItzCrazyKns/Perplexica to ItzCrazyKns/Vane, and the README uses the name Vane throughout. It is the same MIT project, with the same SearXNG-based search and cited answers, and only two deploy links still carry the old name.
No. Vane's Docker image includes SearXNG, a self-hosted metasearch engine, and Morphic's Docker Compose starts one, so neither needs a paid search key. You do need a model, either hosted with an API key or local through Ollama.
Yes. Vane supports Ollama and any local OpenAI-compatible server, Morphic lists Ollama among its providers, and Khoj runs any local model. With SearXNG running alongside, the model and the search engine both stay on your machines.
Morphic, with Supabase sign-in and a guest mode for anonymous use. Vane lists authentication as an upcoming feature, so it suits one person or a trusted network for now. Khoj runs self-hosted or as its makers' hosted and enterprise service.
Running one of these inside your own environment, with your own data and your own security rules, is the kind of work Reveneau does. Read how a forward deployed engagement works.