Simplicity

On your phone?

You install Simplicity from a computer. Send yourself the link and open it there.

Before you start: Answers run on publik API with no key to paste — linking your publik account gives $0.05 of free use once, then the app pays publik's published price per use, and your own key still works. Local models through Ollama are still supported

Available for macOS and Windows.

Built on Publik APIBuild yours →

Runs on publik API

AI chat & tools: Chat completions with tool calls, JSON schemas and images, priced per tier in dollars.

No key to paste.
Linking your publik account gives five cents of free use, once.
Then Simplicity pays publik's published price per use, and your own key still works.

How pricing works

Vote on Simplicity

Read the install guide Open in GitHub

Compared with

Perplexity

$200/mo

What a month of AI costs

Perplexity$200.00/mo
publik API$4.33/mo

publik API: $195.67 a month less than Perplexity.

100 uses a week at the Balanced level, the one Simplicity uses most · publik API is cheaper up to about 4,615 uses a week

Make this yoursFork Simplicity, change it, publish your version. About 30 minutes. No experience needed.

1,067 downloads through publik

Having trouble? Tell us

Where Simplicity’s AI runs, and what it costs

Prices are for one typical use: one request of about 1,500 words sent and 375 words back. A higher quality score is better.

On your computer

Price: Free per use. Your computer does the work.
Runs with: Transformers, Ollama
Memory: Llama 3.1 8B is a 4.9 GB download at 4-bit. gpt-oss 20B runs on systems with as little as 16GB memory. Faster with Apple silicon or a graphics card.
Quality: Llama 3.1 8B: 7

publik API

Price: $0.0100 per use, $10.00 per 1,000 usespublik-balanced, the level Simplicity uses most
Quality: MiMo-V2.6-Pro: 46
Setup: Built in. No key to paste; linking your publik account gives $0.05 of free use, once.

Your own key

Price: $0.0013 per use, $1.31 per 1,000 usesMiMo-V2.6-Pro at OpenRouter’s list price, before its fee for buying usage
Quality: MiMo-V2.6-Pro: 46
Setup: Open a provider account, add a card, paste the key into Simplicity.

Quality and price, side by side

Quality score and cost per 1,000 typical uses for local models and the three publik API levels
Model	Quality	Per 1,000 uses
On your computer (Ollama, 4-bit download size)
Granite 4.2 3B2.2 GB	9	$0
Phi-4 Mini2.5 GB	6	$0
Llama 3.1 8B4.9 GB	7	$0
gpt-oss 20B14 GB	9	$0
Gemma 4 31B20 GB	19*	$0
Qwen3.5 35B-A3B24 GB	19*	$0
publik API
publik-fastGLM-5.3 Flash	42	$1.00
publik-balancedMiMo-V2.6-Pro · Simplicity	46	$10.00
publik-smartGPT-6 Sol	48	$18.00

Quality: Artificial Analysis Intelligence Index v4.3.2, read 2026-09-22 (publik API models 2026-09-25); * = estimated by Artificial Analysis. Sizes: the Ollama library, read 2026-09-22.

What you pay for

On your computer: nothing per use. You pay in disk space, memory and electricity, at lower quality.
publik API: publik’s published price for each use, in dollars, from your publik balance. It is above the model’s cost; the difference runs publik and pays the app’s builder.
Your own key: the provider’s price, billed to an account you keep with the provider.

Install Simplicity: publik API is built in How publik API pricing works

How to install Simplicity

Every step written out. No terminal experience needed. Pick your setup.

README

Open in GitHub

A free, private, Perplexity-style answer engine that runs entirely on your computer. No account. No subscription. Your searches never leave your machine — a local search engine does the searching, and answers come from your own AI models: free local ones, your existing Claude subscription, or your own API keys.

⚠️ Starting point, not a finished product

This is an early beta — a starting point. The core loop (search → sources → cited answer) is solid and tested, but edges are rough: some surfaces are still being brought to parity, and things will change fast. Use it, break it, tell us what broke.

What it does

Search-first answers — every factual question triggers real web retrieval through your own local SearxNG metasearch (7 engines, no single point of failure), then the model writes a cited answer. The model never gets to "answer from memory" on facts.
Behind-the-scenes transparency — watch the exact search queries, every source found, and each research step as it happens.
Deep research — a capped multi-round research loop that scrapes and reads pages, then writes a long-form sectioned report.
Model council — up to 3 models from different vendors answer the same question in parallel from the same sources; a chair model compares them and calls out where they agree and disagree.
Price per query — every answer shows exactly what it cost you ("$0.0042 · 12.4k tokens", per-model breakdown). Local models and Claude-subscription answers show Free.
Your models, your choice — pick per message: local Ollama (free), your Claude plan (free), or GPT-5.1 / Gemini 2.5 Pro / Claude Opus 4.8 / Grok on your keys. Nothing is locked.
Incognito threads — flip the lock and the thread is never written to disk.
Export — Markdown, PDF, or CSV of any answer.
Private by construction — searches run through your local metasearch, chats live in a local SQLite file, API keys stay on your device. There is no server of ours to send anything to.

Credits & license

Simplicity is a fork of Vane by ItzCrazyKns (the successor to Perplexica) — an excellent foundation, rebuilt here as a desktop app with a search-first retrieval pipeline, model council, cost tracking, and the rest of the feature set above. MIT licensed, same as upstream.