Can I vibecode Animam.ai?

What you build

Crawl the sitemap, strip the chrome, store the text, retrieve the 5 best passages by keyword, stream a grounded answer, and refuse to answer outside the context.

what you need

• An LLM API key (Anthropic, OpenAI, or a local model)
• A place to run a small Node server (a 5 EUR VPS is enough)
• SQLite, or any database you already run
• A domain you can serve the widget from

Self-submitted by the people who sell it. The honest verdict is 'kinda', not 'not really': if we claimed our own chat layer could not be rebuilt in a weekend we would be lying, and this audience would know. The prompt below is the real one · it is not weakened to protect the subscription. What it deliberately leaves out is listed in whatYouLose, and that list is the product.

The prompt

A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.

Build a website chat widget that answers strictly from a site's own content. Node 20 + TypeScript, no framework.

1. Install hono, @anthropic-ai/sdk, cheerio, turndown, better-sqlite3.
2. scripts/ingest.ts takes a sitemap.xml URL as argv and fetches every page, concurrency 4, skipping non-HTML.
3. Strip nav, header, footer and script tags with cheerio, then convert what is left to markdown with turndown.
4. Upsert into SQLite pages(url PRIMARY KEY, title, body, fetched_at) so re-running updates rows instead of duplicating them.
5. src/search.ts takes the 3 to 6 most distinctive words of the question and runs SELECT url, title, substr(body,1,1200) FROM pages WHERE body LIKE ? for each.
6. Rank by number of hits and return the top 5. No embeddings: under ~500 pages LIKE is cheaper, instant, and you can read why a passage was picked.
7. src/server.ts is a Hono app with POST /chat {message, sessionId}.
8. Put the 5 passages and their URLs in the system prompt, call claude-haiku with stream:true, and pipe SSE to the client.
9. System prompt: "Answer only from the CONTEXT below, and cite the page you used."
10. Continue it: "If the answer is not in the context, say you do not know and offer to take a message."
11. And the line that matters: "Never state a price, a date or an availability that is not written in the context."
12. public/widget.js is an IIFE that injects a bubble into a shadow DOM and keeps sessionId in localStorage.
13. It consumes the SSE and writes every message with textContent, never innerHTML · the text comes from a model that read the internet.
14. Store sessions and messages in the same SQLite file, so you can read back what people actually asked.
15. ANTHROPIC_API_KEY lives in .env, server-side only, and never reaches the bundle.
16. No telemetry, no third-party script in the widget.
17. Serve /widget.js with CORS * and a 5 minute cache so a single <script> tag installs it on any page.

Out of scope on purpose, and each of these is a week rather than a line: booking on a real calendar, payments,
quotes with amounts computed server-side, human handover, transactional email that reaches the inbox,
multi-tenancy, GDPR consent, rate limiting and abuse protection.

What you lose

• Amounts computed server-side from a price grid · the model picks the SKU, it never produces the number
• Visitor identity verified by one-time code before any server-to-server action runs
• Signed outgoing webhooks with exponential backoff, delivery log and manual redelivery
• SSRF guard with DNS resolution on every URL the agent is allowed to call
• Per-tenant secrets encrypted at rest, and tenant isolation you did not have to think about
• Email deliverability · a warmed sending domain is not something you prompt into existence
• The evening the model provider changes a default and your widget starts making things up

Why people still pay

Because the demo is the easy half. A chat that answers is a weekend; a chat you can leave in front of customers for a year is an operations job · someone watches deliverability, re-crawls the site, keeps the model from inventing a price, and is there the day it breaks. People pay for the second half, and they are right to.

moat: Infrastructure scale Execution quality what a moat is

operations/compliance/deliverability

Who has already built it

Starting from here is still vibecoding: the prompt is for when you want it exactly your way.

• Chatwoot (opens in a new tab) — Self-hosted support inbox with a website widget (open-source)
• Typebot (opens in a new tab) — Open-source conversational forms and chat flows (open-source)
• Onyx (ex-Danswer) (opens in a new tab) — Open-source RAG chat over your own documents (open-source)

Do you agree?