Can Admix be vibe coded?
Multi-model AI chat that compares answers side by side across providers
A local chat UI with side-by-side replies is a contained 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.
Jump to the build brief ↓Checked Aug 2026
What you pay today, before any DIY hosting
high editorial confidence
Buildability by layer
Screens, forms, and focused interactions
The repeatable job the product performs
Availability and legality of required data
Uptime, queues, support, and maintenance
Security, compliance, and user confidence
The achievable core
- Send one prompt to selected models through OpenRouter, stream the replies into a side-by-side grid, and save the thread locally.
- Build a focused single-user workflow with real persistence, search, and export.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- 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
- Connectors, OAuth flows, and vendor API changes require constant upkeep.
- The last 20 percent is sync, migration fidelity, speed, and edge cases.
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.
Connectors, OAuth flows, and vendor API changes require constant upkeep.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
The brief
Context, requirements, acceptance criteria, non-goals, and the full production standard — as Markdown, ready for any coding agent.
Build brief — a focused alternative to Admix
Context
**Admix** — Multi-model AI chat that compares answers side by side across providers. It currently costs $10/mo.
A local chat UI with side-by-side replies is a contained 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.
This brief describes a focused, single-operator replacement for the part of Admix that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.
What you are building
Send one prompt to selected models through OpenRouter, stream the replies into a side-by-side grid, and save the thread locally.
Build a focused single-user workflow with real persistence, search, and export.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
Node 22.
SQLite.
Provider and model IDs to compare.
Data and integrations
OpenRouter API key in.env.
Each of these needs a real account, credential, or quota. Set them up before writing feature code.
Non-functional
Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
Security: server-side secrets, validated input, and no credentials in the client bundle.
Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
Portability: the operator can export their data and leave without losing it.
Implementation brief
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.
Delivery standard
Inspect the repository first, then write a short implementation plan before writing code.
Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
Add structured logs around every external call and return actionable errors without leaking sensitive details.
Write unit tests for the core logic and one automated test of the main user journey.
Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.
Acceptance criteria
A clean install starts the app using only the README and .env.example.
The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
Tests, type checking, linting, and a production build all pass with no ignored failures.
No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.
Non-goals
Do not build these, and do not claim to have replaced them:
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.
Connectors, OAuth flows, and vendor API changes require constant upkeep.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
What you still own after launch
Secure credentials, rotate secrets, and handle provider rate limits.
Run migrations, backups, restores, and dependency updates.
Test the critical journey after every model, API, or hosting change.
Monitor failures and fix the edge cases a first prompt will miss.
Maintain every third-party integration as APIs and OAuth rules change.
Risk
**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.
Editorial confidence in this assessment: high. No independent one-shot implementation is linked yet.
Prior art
Working open-source software you can read, fork, or borrow from before starting:
[Open WebUI](https://github.com/open-webui/open-webui) — Open-source self-hosted chat interface for local and hosted models
[LibreChat](https://github.com/danny-avila/LibreChat) — Open-source multi-model AI chat platform for self-hosting API-based assistants
Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/admix
You still own the product
- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
- Maintain every third-party integration as APIs and OAuth rules change.
Open-source prior art
Before you start
Can Admix be vibe coded?
Partly, if you narrow it. A local chat UI with side-by-side replies is a contained 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.
What can an AI coding agent reproduce from Admix?
Send one prompt to selected models through OpenRouter, stream the replies into a side-by-side grid, and save the thread locally. Build a focused single-user workflow with real persistence, search, and export. A responsive interface with real empty, loading, success, and error states.
What will a DIY Admix replacement still be missing?
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; Connectors, OAuth flows, and vendor API changes require constant upkeep.; The last 20 percent is sync, migration fidelity, speed, and edge cases.
What do I still own after building a Admix alternative?
Secure credentials, rotate secrets, and handle provider rate limits. Run migrations, backups, restores, and dependency updates. Test the critical journey after every model, API, or hosting change. Monitor failures and fix the edge cases a first prompt will miss. Maintain every third-party integration as APIs and OAuth rules change.