PLAI.chat – Multi-model AI chat that doesn't store your conversations

Name: PLAI.chat – Multi-model AI chat that doesn't store your conversations
Availability: InStock
Author: coderai

by coderai·Mar 2, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidDark HorseSolve My Problem

OpenRouter aggregator with verifiable privacy—localStorage-only architecture, but competitors already exist.

Strengths

•Legitimate privacy architecture: no login required, zero server-side conversation retention, verifiable via browser inspection.
•300+ model access via OpenRouter means you're not locked into one provider's release cycle—real problem solved.
•Pay-per-use with no subscription or forced account creation lowers friction compared to ChatGPT/Claude.

Weaknesses

•OpenRouter, Llama, and multi-model aggregators already exist; this is a frontend wrapper, not a novel backend architecture.
•No evidence of adoption or traction beyond landing page claims—privacy pitch alone doesn't differentiate in a crowded space.

Post Description

I built PLAI.chat because I was frustrated with two things: 1) new models ship every week and I was constantly switching between apps to keep up. 2) Every service stores my conversations on their servers.

So, PLAI.chat takes a different approach: your chat history is stored only in your browser's localStorage — never on our servers. API calls go to model providers via OpenRouter, but we don't log, store, or train on any conversations — and they aren't linked to any user identity on our end. We don't store anything. The architecture makes the privacy guarantee verifiable, not just a policy claim.

You can try it right now, no account needed. Go to plai.chat and start chatting for free. For more models or higher limits, sign in with a magic link — no forced registration, no confirmation hoops.

What it does: - 300+ models (GPT, Claude, Gemini, Llama, Mistral, Qwen, and more via OpenRouter) - Free to start, pay-per-use for extended usage — no subscription - Chat history in your browser only — close the tab, it's still there; we never see it - Switch models mid-conversation to compare responses; presets for free/balanced/premium - Supports files, PDFs, images, and image generation

I also built a Slack version — but still waiting on Slack's marketplace approval, which has been... slow.

Stack: Next.js, Cloudflare Workers, Stripe, OpenRouter.

Thanks for your feedback and comments!

Lucas

https://plai.chat

Similar Projects

AI/ML●Mid

LM Canvas – current chat interfaces suck, so I built a canvas for LLMs

Multi-model canvas is clever, but 300+ model support and branching don't solve core UX friction vs. Continue, Claude projects.

Big BrainBold BetShip It

max-lee-dev

213mo ago

AI/ML●●Solid

Sekha – What if AI remembered 3 years of conversations, not 3 hours?

The core idea is simple and pragmatic: attach a persistent, SQLite-backed vector store to any model so conversations don't vanish after a single context window. The repo leans into portability (Rust, self-hosted, AGPL) and the UI shows sensible controls like conversation folders and a context-budget token slider — useful details that suggest this is built for real use rather than a demo. My worry: retrieval quality, scaling and access controls will be the real battleground, not the clean chat UI.

Niche GemSolve My Problem

sekha-ai

113mo ago

Gaming●●●Banger