AI assistants and search decision
Otherwise
With no public docs or pricing available, a technical user can recreate a narrow assistant workflow reasonably quickly, but the full commercial product's value (branding, proprietary models/integrations, and polish) cannot be reproduced from the provided page.
Visit website↗Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off40 h to build
$50/mo3 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 Otherwise alternatives, with the arithmetic →
What a replacement has to do
- A minimal self-hosted assistant that accepts user text, calls an LLM, stores conversation history, and serves a web chat UI.
What it still won’t have
- Brand-recognition, existing user base and trust
- Any proprietary models, closed-source integrations, or private data the vendor owns
- Polish and product UX refinements present in a commercial offering
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Otherwise 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
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
Build a minimal self-hosted AI chat assistant using Next.js for the frontend, Node.js + Express for the API, Postgres for conversation storage, and OpenAI-compatible API calls for LLM responses. Core features: user sign-up/login (email+password), a streaming web chat interface, message persistence and retrieval, simple rate limiting, and deployment scripts for a single VPS (Docker Compose). Out of scope: advanced analytics, multi-tenant billing, proprietary models, and voice/chatbot integrations. Include error handling, input validation, basic tests for API endpoints, and README with deployment steps.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 3 cited sources+3
- Evidence score60
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.
- official productOtherwise — official product
- open sourceChatGPTNextWeb/NextChat
- open sourceCherryHQ/cherry-studio
Integrity checks
What held up, and what did not.
