[verdict][curated prompt][source: admix.software]
Can I vibecode Admix?
// buildable in a weekend, but real gaps stay open
A local chat UI with side-by-side replies is a weekend project when it calls OpenRouter, but Admix's value depends on access to many hosted models, a current catalog, provider routing, and a maintained account and billing layer. You can reproduce the comparison workflow. You cannot reproduce the model access and service layer for a flat $10 subscription.
confidence: high
what it is: Multi-model AI chat that compares answers side by side across providers
Buildability index · an editorial game
- Price 10 $/month weight: plus 1
- Time weekend weight: plus 2
- Category ai assistants no weight
- Moat integrations · execution quality weight: minus 2
- Confidence high weight: plus 1
- What you lose 5 items weight: minus 2
- Site admix.software (si apre in una nuova scheda) no weight
They cancel out. This is where it comes down to how much the subscription annoys you.
Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.
What you build
Send one prompt to selected models through OpenRouter, stream the replies into a side-by-side grid, and save the thread locally.
what you need
- Node 22
- OpenRouter API key in .env
- SQLite
- Provider and model IDs to compare
The interface is easy to reproduce; the useful question is whether the API bill and missing provider features still work for you.
The prompt
A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.
Build me a local multi-model comparison chat to replace Admix. Requirements:
- Node 22 + Express + better-sqlite3, a server-rendered shell with a little vanilla
JS for streaming; no frontend framework, no build step.
- One OpenRouter key in .env, kept server-side; the server proxies all model calls.
- A model picker fed from OpenRouter's /models endpoint; select up to four models.
- One prompt fans out to the selected models and streams each reply into a
side-by-side grid with model name, elapsed time, and token usage when reported;
a failed model shows its error in its own column without killing the others.
- Markdown rendering with fenced code blocks and a copy button per reply.
- Threads, prompts, model ids, replies, and timestamps in SQLite; full-text search
across saved threads; export a thread as Markdown.
- A running cost estimate per thread from OpenRouter's usage and pricing fields.
- Binds to localhost only. No accounts, no telemetry; prompts and replies leave the
machine only for OpenRouter, and the README says so.
- Out of scope: auth, billing, mobile apps, image generation, hosted sync, and
provider-specific tools like web search or file upload.
- README: setup, .env.example, and how to add a model id by hand if the catalog
fetch fails.Curated prompt: written and reviewed by hand for this app. In English on purpose — it is the language coding agents work best in.
What you lose
- Admix's bundled access to many providers under one subscription
- A maintained model catalog and provider routing
- Cross-device sync and account history
- Built-in image, search, and document workflows
- Usage limits, billing, and support handled for you
Why people still pay
They pay for one bill and one interface instead of managing several provider accounts, API keys, model IDs, and usage limits. The comparison grid is easy to copy; keeping model access and the account, billing, and storage layer working is the service.
moat: Integrations Execution quality what a moat is
bundled model access, catalog upkeep, and billing under one subscription
Free alternatives
Not in the mood to build it? These already exist, they are free or open source, and we checked them one by one.
Cherry Studio open source (si apre in una nuova scheda) 49.9k ★ Aug 2026 one-click deploy Same prompt, several models, side by side; bring API keys or make local models do the arguing. 
Open WebUI free (si apre in una nuova scheda) — — one-click deploy Run several models in parallel columns and merge the result; free to run, source-available rather than open source. Cherry Studio open source (si apre in una nuova scheda) 49.9k ★ Aug 2026 one-click deploy A desktop model cockpit with parallel answers, files, agents, and rather more settings than restraint. Rejected (2) — and why
- Msty (si apre in una nuova scheda) — The desktop core is $0, but the terms limit it to private non-commercial use; paid work needs a license.
- LibreChat (si apre in una nuova scheda) — A polished multi-provider chat, but it does not send one prompt to several models side by side.
Who has already built it
Starting from here is still vibecoding: the prompt is for when you want it exactly your way.
- Open WebUI (opens in a new tab) — Open-source self-hosted chat interface for local and hosted models.
- LibreChat (opens in a new tab) — Open-source multi-model AI chat platform for self-hosting API-based assistants.
Do you agree?
The vote balance
Ancora nessun voto: il tuo è il primo.
Nessun voto ancora — il primo pesa.
