Vibecode MagicChat

You are building a lean indie version of MagicChat.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== README.md =====
# MagicChat indie build

## Goal

Build the smallest trustworthy replacement for the core MagicChat workflow for one developer or a tiny team.

## Scope

Crawl a site or docs, chunk and embed the pages into a vector store, retrieve the top matches for a visitor question, and answer with an LLM through an embeddable chat widget.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- scheduled auto re-crawl and content refresh
- analytics and conversation-history dashboards
- lead capture and human handoff
- multi-source connectors and integrations
- hosted uptime for the widget
- team seats and enterprise compliance (HIPAA/DPA/BAA)

If those capabilities are essential, use Onyx (formerly Danswer) instead of pretending the gap is solved.

===== AGENTS.md =====
# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

===== BUILD_PLAN.md =====
# Build plan

## Original build brief

Build me an AI support chatbot that trains on my own website and docs, to replace
MagicChat, in an empty repo.

Stack (no alternatives): Next.js 15 (App Router) + TypeScript, Postgres with the
pgvector extension via Drizzle ORM, and Docker Compose so `docker compose up` runs
Postgres and the app together. Use the OpenAI or Anthropic API for both embeddings
and answers (keys in .env).

Core loop:
- `npm run ingest -- <sitemap-or-url>`: crawl the pages, strip to clean text, chunk
  (~800 tokens with overlap), embed each chunk, and store text + vector + source URL
  in Postgres.
- A /api/chat route: embed the incoming question, pull the top-k chunks by cosine
  similarity, and ask the LLM to answer ONLY from that context, returning the source
  URLs it used. Stream the answer.
- A single embeddable widget: one <script> tag mounts a floating chat bubble on any
  site, talking to /api/chat with CORS locked to configured origins.

Details:
- One config file: bot name, greeting, allowed origins, model, top-k.
- Store everything locally in Postgres; `npm run reindex` re-crawls and replaces.
- Secrets in .env, ship .env.example, never commit keys.
- Handle empty, loading, and "I don't know from the docs" states honestly; never
  invent answers outside the retrieved context.
- Out of scope: multi-channel (email/WhatsApp/Slack), team seats, an analytics
  dashboard, human handoff, scheduled auto-refresh (leave a documented cron hook),
  and any hosted control plane.
- README: setup, the ingest command, embedding the widget, and where data lives.

## Required capabilities

- OpenAI/Anthropic API key
- an embeddings model
- a vector store (pgvector or sqlite-vec)
- a public HTTPS deployment for the widget

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

===== .env.example =====
# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

You are building a lean indie version of MagicChat.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== README.md =====
# MagicChat indie build

## Goal

Build the smallest trustworthy replacement for the core MagicChat workflow for one developer or a tiny team.

## Scope

Crawl a site or docs, chunk and embed the pages into a vector store, retrieve the top matches for a visitor question, and answer with an LLM through an embeddable chat widget.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- scheduled auto re-crawl and content refresh
- analytics and conversation-history dashboards
- lead capture and human handoff
- multi-source connectors and integrations
- hosted uptime for the widget
- team seats and enterprise compliance (HIPAA/DPA/BAA)

If those capabilities are essential, use Onyx (formerly Danswer) instead of pretending the gap is solved.

===== AGENTS.md =====
# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

===== BUILD_PLAN.md =====
# Build plan

## Original build brief

Build me an AI support chatbot that trains on my own website and docs, to replace
MagicChat, in an empty repo.

Stack (no alternatives): Next.js 15 (App Router) + TypeScript, Postgres with the
pgvector extension via Drizzle ORM, and Docker Compose so `docker compose up` runs
Postgres and the app together. Use the OpenAI or Anthropic API for both embeddings
and answers (keys in .env).

Core loop:
- `npm run ingest -- <sitemap-or-url>`: crawl the pages, strip to clean text, chunk
  (~800 tokens with overlap), embed each chunk, and store text + vector + source URL
  in Postgres.
- A /api/chat route: embed the incoming question, pull the top-k chunks by cosine
  similarity, and ask the LLM to answer ONLY from that context, returning the source
  URLs it used. Stream the answer.
- A single embeddable widget: one <script> tag mounts a floating chat bubble on any
  site, talking to /api/chat with CORS locked to configured origins.

Details:
- One config file: bot name, greeting, allowed origins, model, top-k.
- Store everything locally in Postgres; `npm run reindex` re-crawls and replaces.
- Secrets in .env, ship .env.example, never commit keys.
- Handle empty, loading, and "I don't know from the docs" states honestly; never
  invent answers outside the retrieved context.
- Out of scope: multi-channel (email/WhatsApp/Slack), team seats, an analytics
  dashboard, human handoff, scheduled auto-refresh (leave a documented cron hook),
  and any hosted control plane.
- README: setup, the ingest command, embedding the widget, and where data lives.

## Required capabilities

- OpenAI/Anthropic API key
- an embeddings model
- a vector store (pgvector or sqlite-vec)
- a public HTTPS deployment for the widget

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

===== .env.example =====
# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

You are building a production product version of MagicChat.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== PRODUCT.md =====
# MagicChat product brief

## Problem

A retrieval chatbot over your own docs is one of the most one-shottable products there is: crawl the site, chunk and embed it, answer from the top matches with an LLM, drop in a widget. What you don't get for free is the boring operational layer, scheduled re-crawls, analytics, lead capture and human handoff, multi-source connectors, and a hosted widget that stays up. Buildable in a weekend, real gaps after that.

## Product outcome

Crawl a site or docs, chunk and embed the pages into a vector store, retrieve the top matches for a visitor question, and answer with an LLM through an embeddable chat widget.

## Target user

A serious builder who needs a maintainable product foundation rather than a one-off demo.

## Required capabilities

- OpenAI/Anthropic API key
- an embeddings model
- a vector store (pgvector or sqlite-vec)
- a public HTTPS deployment for the widget

## Explicit non-goals for v1

- scheduled auto re-crawl and content refresh
- analytics and conversation-history dashboards
- lead capture and human handoff
- multi-source connectors and integrations
- hosted uptime for the widget
- team seats and enterprise compliance (HIPAA/DPA/BAA)

## Success criteria

- The primary workflow is measurable end to end.
- Setup is reproducible in a clean environment.
- Failure, recovery, and support paths are documented.
- Product claims match what the implementation actually guarantees.

===== ARCHITECTURE.md =====
# Architecture

## Starting brief

Build me an AI support chatbot that trains on my own website and docs, to replace
MagicChat, in an empty repo.

Stack (no alternatives): Next.js 15 (App Router) + TypeScript, Postgres with the
pgvector extension via Drizzle ORM, and Docker Compose so `docker compose up` runs
Postgres and the app together. Use the OpenAI or Anthropic API for both embeddings
and answers (keys in .env).

Core loop:
- `npm run ingest -- <sitemap-or-url>`: crawl the pages, strip to clean text, chunk
  (~800 tokens with overlap), embed each chunk, and store text + vector + source URL
  in Postgres.
- A /api/chat route: embed the incoming question, pull the top-k chunks by cosine
  similarity, and ask the LLM to answer ONLY from that context, returning the source
  URLs it used. Stream the answer.
- A single embeddable widget: one <script> tag mounts a floating chat bubble on any
  site, talking to /api/chat with CORS locked to configured origins.

Details:
- One config file: bot name, greeting, allowed origins, model, top-k.
- Store everything locally in Postgres; `npm run reindex` re-crawls and replaces.
- Secrets in .env, ship .env.example, never commit keys.
- Handle empty, loading, and "I don't know from the docs" states honestly; never
  invent answers outside the retrieved context.
- Out of scope: multi-channel (email/WhatsApp/Slack), team seats, an analytics
  dashboard, human handoff, scheduled auto-refresh (leave a documented cron hook),
  and any hosted control plane.
- README: setup, the ingest command, embedding the widget, and where data lives.

## Boundaries

Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors.

## Production baseline

- Configuration: validated at startup with safe local defaults where possible.
- Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives.
- Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions.
- Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts.
- Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists.
- Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test.

## Decision records

For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.

===== AGENTS.md =====
# Agent instructions

- Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code.
- Implement milestone by milestone; keep each change reviewable and leave the application runnable.
- Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present.
- Never invent cryptography or silently weaken a requirement to make a test pass.
- Use provider interfaces for external services and deterministic fakes in tests.
- Add migrations and rollback or recovery notes for persistent data changes.
- Log useful operational context without credentials, tokens, passwords, or personal data.
- Update documentation and run all checks before completing a milestone.

===== MILESTONES.md =====
# Delivery milestones

## M0 — Decisions and scaffold

- Confirm the runtime, persistence model, threat boundaries, and deployment target.
- Create a reproducible local environment and continuous checks.

## M1 — Core workflow

- Implement the smallest end-to-end product path with validation and tests.
- Keep integrations behind interfaces.

## M2 — Trust layer

- Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards.
- Test abuse cases and destructive operations.

## M3 — Operability

- Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration.

## M4 — Release gate

- Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise.
- Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.

===== OPERATIONS.md =====
# Operations

## Before release

- Validate configuration and secrets at startup.
- Define backup, restore, and rollback procedures and test them.
- Document logs, error tracking, health signals, and alert ownership.
- Set dependency update and vulnerability review expectations.

## Incident checklist

1. Contain the issue without destroying evidence or user data.
2. Record the timeline and affected scope.
3. Rotate exposed secrets and revoke compromised sessions or credentials.
4. Restore from a verified source when needed.
5. Document the root cause, remediation, and regression test.

## Launch constraint

Do not market omitted MagicChat capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

# MagicChat indie build

## Goal

Build the smallest trustworthy replacement for the core MagicChat workflow for one developer or a tiny team.

## Scope

Crawl a site or docs, chunk and embed the pages into a vector store, retrieve the top matches for a visitor question, and answer with an LLM through an embeddable chat widget.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- scheduled auto re-crawl and content refresh
- analytics and conversation-history dashboards
- lead capture and human handoff
- multi-source connectors and integrations
- hosted uptime for the widget
- team seats and enterprise compliance (HIPAA/DPA/BAA)

If those capabilities are essential, use Onyx (formerly Danswer) instead of pretending the gap is solved.

# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

# Build plan

## Original build brief

Build me an AI support chatbot that trains on my own website and docs, to replace
MagicChat, in an empty repo.

Stack (no alternatives): Next.js 15 (App Router) + TypeScript, Postgres with the
pgvector extension via Drizzle ORM, and Docker Compose so `docker compose up` runs
Postgres and the app together. Use the OpenAI or Anthropic API for both embeddings
and answers (keys in .env).

Core loop:
- `npm run ingest -- <sitemap-or-url>`: crawl the pages, strip to clean text, chunk
  (~800 tokens with overlap), embed each chunk, and store text + vector + source URL
  in Postgres.
- A /api/chat route: embed the incoming question, pull the top-k chunks by cosine
  similarity, and ask the LLM to answer ONLY from that context, returning the source
  URLs it used. Stream the answer.
- A single embeddable widget: one <script> tag mounts a floating chat bubble on any
  site, talking to /api/chat with CORS locked to configured origins.

Details:
- One config file: bot name, greeting, allowed origins, model, top-k.
- Store everything locally in Postgres; `npm run reindex` re-crawls and replaces.
- Secrets in .env, ship .env.example, never commit keys.
- Handle empty, loading, and "I don't know from the docs" states honestly; never
  invent answers outside the retrieved context.
- Out of scope: multi-channel (email/WhatsApp/Slack), team seats, an analytics
  dashboard, human handoff, scheduled auto-refresh (leave a documented cron hook),
  and any hosted control plane.
- README: setup, the ingest command, embedding the widget, and where data lives.

## Required capabilities

- OpenAI/Anthropic API key
- an embeddings model
- a vector store (pgvector or sqlite-vec)
- a public HTTPS deployment for the widget

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

# MagicChat product brief

## Problem

A retrieval chatbot over your own docs is one of the most one-shottable products there is: crawl the site, chunk and embed it, answer from the top matches with an LLM, drop in a widget. What you don't get for free is the boring operational layer, scheduled re-crawls, analytics, lead capture and human handoff, multi-source connectors, and a hosted widget that stays up. Buildable in a weekend, real gaps after that.

## Product outcome

Crawl a site or docs, chunk and embed the pages into a vector store, retrieve the top matches for a visitor question, and answer with an LLM through an embeddable chat widget.

## Target user

A serious builder who needs a maintainable product foundation rather than a one-off demo.

## Required capabilities

- OpenAI/Anthropic API key
- an embeddings model
- a vector store (pgvector or sqlite-vec)
- a public HTTPS deployment for the widget

## Explicit non-goals for v1

- scheduled auto re-crawl and content refresh
- analytics and conversation-history dashboards
- lead capture and human handoff
- multi-source connectors and integrations
- hosted uptime for the widget
- team seats and enterprise compliance (HIPAA/DPA/BAA)

## Success criteria

- The primary workflow is measurable end to end.
- Setup is reproducible in a clean environment.
- Failure, recovery, and support paths are documented.
- Product claims match what the implementation actually guarantees.

# Architecture

## Starting brief

Build me an AI support chatbot that trains on my own website and docs, to replace
MagicChat, in an empty repo.

Stack (no alternatives): Next.js 15 (App Router) + TypeScript, Postgres with the
pgvector extension via Drizzle ORM, and Docker Compose so `docker compose up` runs
Postgres and the app together. Use the OpenAI or Anthropic API for both embeddings
and answers (keys in .env).

Core loop:
- `npm run ingest -- <sitemap-or-url>`: crawl the pages, strip to clean text, chunk
  (~800 tokens with overlap), embed each chunk, and store text + vector + source URL
  in Postgres.
- A /api/chat route: embed the incoming question, pull the top-k chunks by cosine
  similarity, and ask the LLM to answer ONLY from that context, returning the source
  URLs it used. Stream the answer.
- A single embeddable widget: one <script> tag mounts a floating chat bubble on any
  site, talking to /api/chat with CORS locked to configured origins.

Details:
- One config file: bot name, greeting, allowed origins, model, top-k.
- Store everything locally in Postgres; `npm run reindex` re-crawls and replaces.
- Secrets in .env, ship .env.example, never commit keys.
- Handle empty, loading, and "I don't know from the docs" states honestly; never
  invent answers outside the retrieved context.
- Out of scope: multi-channel (email/WhatsApp/Slack), team seats, an analytics
  dashboard, human handoff, scheduled auto-refresh (leave a documented cron hook),
  and any hosted control plane.
- README: setup, the ingest command, embedding the widget, and where data lives.

## Boundaries

Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors.

## Production baseline

- Configuration: validated at startup with safe local defaults where possible.
- Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives.
- Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions.
- Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts.
- Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists.
- Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test.

## Decision records

For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.

# Agent instructions

- Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code.
- Implement milestone by milestone; keep each change reviewable and leave the application runnable.
- Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present.
- Never invent cryptography or silently weaken a requirement to make a test pass.
- Use provider interfaces for external services and deterministic fakes in tests.
- Add migrations and rollback or recovery notes for persistent data changes.
- Log useful operational context without credentials, tokens, passwords, or personal data.
- Update documentation and run all checks before completing a milestone.

# Delivery milestones

## M0 — Decisions and scaffold

- Confirm the runtime, persistence model, threat boundaries, and deployment target.
- Create a reproducible local environment and continuous checks.

## M1 — Core workflow

- Implement the smallest end-to-end product path with validation and tests.
- Keep integrations behind interfaces.

## M2 — Trust layer

- Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards.
- Test abuse cases and destructive operations.

## M3 — Operability

- Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration.

## M4 — Release gate

- Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise.
- Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.

# Operations

## Before release

- Validate configuration and secrets at startup.
- Define backup, restore, and rollback procedures and test them.
- Document logs, error tracking, health signals, and alert ownership.
- Set dependency update and vulnerability review expectations.

## Incident checklist

1. Contain the issue without destroying evidence or user data.
2. Record the timeline and affected scope.
3. Rotate exposed secrets and revoke compromised sessions or credentials.
4. Restore from a verified source when needed.
5. Document the root cause, remediation, and regression test.

## Launch constraint

Do not market omitted MagicChat capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

$ choose a build depth, inspect the files, then open the complete pack in your agent