Everyday Helper Chat

Live

Ask anything by text, voice, or photo and get answers plus images.

musemuse-everyday-helper-chat.vercel.appOpen

Get it

The Android app isn't ready yet.

There's no iPhone download. Add it to your Home Screen, and it opens like an app.

Scan it with your iPhone.

Each line is what the check ran on, and no more.

Passed Typecheck · Nov 1, 2026
Passed Build · Nov 1, 2026
Passed The built app starts · Nov 1, 2026
Passed No errors in the browser console · Nov 1, 2026
Passed Smoke test of the main flow · Nov 1, 2026
Passed Its manifest is valid · Nov 1, 2026
Passed MCP server: listed 3 tools, called ask_anything and make_image · Nov 1, 2026
Passed CLI: ran ask_anything and printed JSON · Nov 1, 2026
Passed Claude plugin: its manifest and MCP address check out · Nov 1, 2026
Passed Muse gadget commands: 3 commands check out, and ask_anything ran and printed JSON · Nov 1, 2026
Passed Skill file: Muse Code used it to run ask_anything · Nov 1, 2026

This is a model's opinion, not proof.

Nothing here should be taken as tested.

Not checked Whether its answers are true
Not checked Installing the Claude plugin or the Muse gadget pack on a real device
Not checked ChatGPT: not tested here · Nov 1, 2026

The person left a text note asking for a general chatbot that answers anything with text, photo, and voice input plus image making.

Muse WonderAnswers questions, reads photos, and runs web search in Chat ask mode
Muse ImageGenerates new pictures and edits an uploaded photo in Chat and Studio
Voice TranscribeTurns short recorded voice notes into plain text in Chat
SAM 3.1Finds and outlines named things in a Studio photo

Answers can be incomplete or out of date. An answer with no sources says so.
Voice replies use the browser built in speech synthesis.
Speech input works from recorded files only, not live streams, and returns one plain transcript.
Image edits change the whole frame or a cropped region pasted back, not exact pixels.
Object outlines are estimates and can miss hidden or small objects.
Structured nearby places, events, and paper records are not included in this web and phone version.
History stays in the browser only. No accounts and no other services or keys.
One run should cost cents. Heavy image or long chat use can hit the daily budget.
Long documents are read at a practical size per call, footnotes list what a search returned, and one run stays within the product daily budget.
Text inside images can come out wrong, size sets only the aspect ratio, and search-grounded images are illustrations.

Add it in the Muse app as a custom connector. It exposes 3 actions: ask_anything, make_image, transcribe_clip.

Muse Code made 62 tool calls and 16 edits across 16 files (+1446 −36).
npm run verify passed on the first try.
Screenshot judge: pass. Final Studio screen shows Your picture of an orange tabby on a blue bench matching the prompt with Download and Share.
Built in 14 min for about $0.19 in model calls (est.).
How it was built: 62 tool calls, 16 edits touching 16 files { Read text file `app/layout.tsx`. Read text file `app/muse-app.css`. Read text file `inspo/README.md`. Read text file `musemuse.schema.json`. Read text file `app/globals.css`. { <read-skill-result name="muse-app-ui" status="ok"> <read-skill-result name="meta-reasoning" status="ok"> <read-skill-result name="meta-image" status="ok"> <read-skill-result name="meta-voice" status="ok"> <read-skill-result name="meta-sam" status="ok"> <read-skill-result name="recipe-api" status="ok"> <read-skill-result name="recipe-image" status="ok"> <read-skill-result name="recipe-voice" status="ok"> <read-skill-result name="product-ui" status="ok"> <read-skill-result name="verify" status="ok"> <read-skill-result name="muse-native" status="ok"> Read text file `lib/meta/parts.ts`.