Four short walks. Pick the one that matches your question.

Ask and check, memory, connectors, and receipts. Each one opens a real screen from the app.

Open the DreamerOS GPT or the app and type the messiest version of your real question. Nothing to configure first.

Try it free. No card, ever.

An answer being checked in the app — The app, checking an answer before you see it

Ask and check Memory Connectors Receipts

Ask and check

You ask. It checks before you ever see the answer.

This is that check happening, before the answer reaches you. Ask normally, the way you already type, no account required to start. Up to five checkers that did not write the answer read it back: a hallucination scan, a source check, a drift check, and a confidence check that catches a guess and marks it as a guess. You see the verdict under the answer.

How this works

entrypoints: GPT store (no account) or the DreamerOS app (free account) same pipeline both doors pre-check -> engine -> post-check -> record checkers: DeepSeek, Moonshot, Zhipu, Alibaba, Mistral no checker shares a maker with the engine that answered see the full walk: getting started

Memory

What you said in one tool is known in the next.

This is that one memory surface. Tell ChatGPT something Monday, switch to Claude Wednesday, and it already knows it. The memory lives at the DreamerOS layer, not trapped inside one vendor account, so it follows you instead of resetting every time you change tools. 100 memories free, up to 100,000 on Elite.

How this works

one memory store, reached from ChatGPT, Claude, the web app and your own client over a key you hold rows per plan: 100 / 1,000 / 1,000 / 10,000 / 100,000

Connectors

Where it connects, and what it may do there.

This is the connect screen, showing what is linked. Add DreamerOS to Claude, ChatGPT, Perplexity, or another MCP-aware client with a key from your profile. Once connected, every read from that tool is treated as reading material, never as an order, and nothing it can send, post, or spend goes out without your yes.

How this works

connector action: intent check runs before the call pass = go, flag = go with a marker, fail = HTTP 403 with the reason see the full setup: connect setup

The connect screen showing what is linked — The connect screen, showing what is linked

Receipts

Every answer leaves a record you can open.

This is one such record, open in three layers. Each answer writes one row: which engine answered, what it cost, which checks ran and what they found. Plain words first, so you can stop reading at the layer you need. On Light, receipts land 25 a day. Every paid plan has no daily cap.

How this works

one row per answer: engine, model, cost_usd, tokens_in, tokens_out, pre-check status, post-check status read them in the app under Trust

A receipt open in the app — A receipt, open in the app