Our rating: 3/5 for this setup

A self-hosted Perplexity alternative with Vane and Ollama

The writer stopped paying for Perplexity and runs Vane locally in Docker. It searches the web through SearXNG, hands the results to a model running in Ollama and returns a direct answer with citations you can open. Speed, Balanced and Quality modes trade time for depth. It can also limit a search to discussions or academic papers, answer questions about an uploaded file, or stick to sites you trust.

New Added Nov 2, 2026 · ✓ Last checked Nov 2, 2026

It broke for meBroke?

Diagram drawn by AppToBot from this recipe's source. It shows the flow, not a screenshot of the product.

Setup steps

Install Ollama and pull a model (an embedding model is optional)
Run the Vane Docker container, which includes SearXNG
Open localhost:3000 and connect Ollama on the setup screen
Pick your models and how data is stored
Choose Speed, Balanced or Quality mode for each question

Steps summarized from the original Blog source ↗. Use “Copy” to grab them with the tools and source link, or copy an AI prompt.

How it went

The writer says the only thing they lost was the monthly bill: Vane gives a Perplexity-like answer with sources, and setup took a few minutes once the models had downloaded.

Worth knowing

A weak model can get good sources and still write a poor answer. Leave memory for the retrieved pages: a model that barely fits in normal chat becomes very slow once Vane feeds it several websites.

Only what the original source ↗ says, re-read Nov 2, 2026. How we write these

Try it with AI

Paste this into ChatGPT, Claude or your own agent for step-by-step help. Prompt written by AppToBot from this recipe's data, not by the original author. It keeps drafts for your review and asks before anything is sent or paid.

Help me set up this automation using Vane (formerly Perplexica, with SearXNG built in) + Ollama: "A self-hosted Perplexity alternative with Vane and Ollama".
Goal: replace Perplexity Pro.

How it should work:
- Trigger: You ask a question
- Then: SearXNG searches several engines
- Then: A local model reads the pages
- Then: It writes an answer with citations
- Result: A cited answer, with history kept locally

Setup steps (summarized from the original source):
1. Install Ollama and pull a model (an embedding model is optional)
2. Run the Vane Docker container, which includes SearXNG
3. Open localhost:3000 and connect Ollama on the setup screen
4. Pick your models and how data is stored
5. Choose Speed, Balanced or Quality mode for each question

Guide me one step at a time. Ask me for anything you need (accounts, sheet or channel names) before you start.

Safety rules:
- Build and test with sample data first, and show me a sample result before anything goes live.
- Keep anything that goes to other people (emails, posts, replies, record updates) as drafts for my review until I say otherwise.
- Never send, post, buy, pay, delete or change records without my approval.
- Tell me about any cost (paid plans, API usage) before I'd incur it, and help me set a spending limit.
- Keep API keys and passwords out of shared docs and chats.
- Privacy: Search history stays local in the Docker volume; queries go out to the search engines SearXNG uses.

Based on: https://www.xda-developers.com/made-own-perplexity-locally-only-lost-monthly-bill/

Perplexity ProVane (formerly Perplexica, with SearXNG built in) + Ollama

Tool names link to each official site (opens in a new tab).

Cost afterFree on your own computer

SetupMedium · Not reported

Time savedNot reported

SkillIntermediate

Running cost: Free to run Open-source app and local models on the writer's own computer. Self-hosted How we sort costs
Stack: Ollama
Replace an app: AI bots that replace Perplexity

App vs bot, side by side

Old app vs bot
	Old app / habit	Bot
Tool	Perplexity Pro	Vane + Ollama in Docker at localhost:3000
Monthly cost	Not reported	Free on your own computer
Setup	None (already in use)	Not reported · Intermediate
Your time	Baseline	Not reported
Maintenance	Handled by vendor/you as before	Update the Docker image and models; most of the setup time is downloading models.
Privacy	Data stays with the app vendor	Search history stays local in the Docker volume; queries go out to the search engines SearXNG uses.

Full comparison

Replaces	Perplexity Pro
Bot / agent stack	Vane + Ollama in Docker at localhost:3000
Monthly cost before	Not reported
Monthly cost after	Free on your own computer
Setup time	Not reported
Time saved	Not reported
Skill level	Intermediate
Reliability	3/5: firsthand use of a maintained open-source project, but answer quality depends on your model and there are no figures.
Maintenance	Update the Docker image and models; most of the setup time is downloading models.
Privacy & data	Search history stays local in the Docker volume; queries go out to the search engines SearXNG uses.
Best for	People with a capable computer who want cited answers privately
Not for	People who want the best answers on a laptop with little memory

Pros and cons

Pros

No account or subscription
Citations on every answer
Search modes, file uploads and domain-limited search

Cons

Answer quality depends on the model your computer can run
Quality Mode is slow on a local model

Source and evidence

First-person XDA Developers article (Aug 2026). The writer says the experience is 'almost as good' as Perplexity. No usage period or accuracy figures.

Read the original Blog source ↗

“Not reported” means the source doesn't say. We never fill gaps with guesses. Numbers marked “per author” or “vendor claim” are the source's own and weren't independently tested. Source last checked Nov 2, 2026.

Our rating is an editorial opinion based on the public source above, not lab testing. Spot an error? Request a correction.

Plain-text summary (for search and AI assistants)

A self-hosted Perplexity alternative with Vane and Ollama. Replaces Perplexity Pro with Vane + Ollama in Docker at localhost:3000. Cost before: Not reported. Cost after: Free on your own computer. Setup: Not reported, Intermediate. Time saved: Not reported. Reliability 3/5: 3/5: firsthand use of a maintained open-source project, but answer quality depends on your model and there are no figures. Best for: People with a capable computer who want cited answers privately. Not for: People who want the best answers on a laptop with little memory. How it went (per source): The writer says the only thing they lost was the monthly bill: Vane gives a Perplexity-like answer with sources, and setup took a few minutes once the models had downloaded. Worth knowing: A weak model can get good sources and still write a poor answer. Leave memory for the retrieved pages: a model that barely fits in normal chat becomes very slow once Vane feeds it several websites. Source: https://www.xda-developers.com/made-own-perplexity-locally-only-lost-monthly-bill/

Compare with another recipe ← All recipes

Questions, corrections or ideas?

Spotted an error, want a recipe covered, or have a partnership idea? Send us a message and we'll get back to you.

Starting your own newsletter? Try beehiiv ↗

What is beehiiv?

beehiiv is a newsletter platform: you write and send emails, host a newsletter website, and grow and monetize a list from one place. We've used it for our own newsletter.

beehiiv says (vendor claims, not tested by us):

Free plan with up to 2,500 subscribers and unlimited sends
Built-in website, recommendation network and analytics
0% cut of paid subscription revenue (Stripe fees apply)

Good for: starting or growing an email newsletter. Not ideal for: email automations or removing beehiiv branding on a $0 budget (those need Lite or Pro).

Free plan: $0, no card needed. Paid plans from $49/mo billed annually (Lite, up to 1,000 subscribers). People who sign up through our link get a 14-day trial plus 20% off their first 3 months, per beehiiv's partner page. Facts as of Oct 2026, from beehiiv's own website. More about beehiiv →