AI assistants and search decision

WormGPT

A competent technical user can reproduce the core functionality (chat + code + images) by self-hosting existing open-source assistants and wiring them to model/image APIs; doing so trades away vendor hosting, brand, and any proprietary models or services.

Visit website
You pay

Not priced

No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.

You’d pay instead

$100one-off64 h to build

$50/mo6 h/mo upkeep

No published price to break even against.

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All WormGPT alternatives, with the arithmetic →

What a replacement has to do

  • A minimal replacement serves a web chat UI that proxies user prompts to one or more LLM/image‑generation backends, persists conversation history, and returns model responses and images to the user.

What it still won’t have

  • The vendor's hosted infra, uptime SLAs and scaling
  • Any proprietary trained models or vendor-specific optimizations
  • Brand, discovery, and any bundled content or community
  • Potentially simpler UX polish, analytics, and built-in billing

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

No published price

WormGPT does not publish a price we could read, so there is nothing to compare against. What building costs is below.

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal self-hosted AI chat+image assistant using Next.js for the frontend, FastAPI for the backend, Postgres for conversation storage, and Docker for deployment. Core features in scope: user session handling, streaming chat UI, proxying prompts to one configurable LLM/text API and one image-generation API, persist/retrieve conversations, simple API-key admin auth, containerized deploy scripts, logging, and unit tests for API endpoints. Explicitly out of scope: training models, paid billing integration, advanced moderation workflows, and multi-tenant SaaS billing. Include error handling, input validation, and basic end-to-end tests.
How we checked3 sources · 2/3 runs agreed · evidence score 86

How the score was reached

  • Build verdict base78
  • An open-source build was found+5
  • 3 cited sources+3
  • Evidence score86

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 3

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat recorded