Vibecode Nsketch AI

You are building a lean indie version of Nsketch AI.

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 =====
# Nsketch AI indie build

## Goal

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

## Scope

Submit a prompt to one user-supplied media API, track the image or video job, review outputs in a private gallery, and export files with reproducible settings.

## 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:
- a broad, continuously updated catalog of image, video, voice, and motion models
- managed queues, concurrency, credits, retries, and provider failover
- hosted media storage, delivery, and cross-device asset history
- ready-made viral templates, editing utilities, and creator workflows
- production moderation, consent controls, support, and commercial operations

If those capabilities are essential, use ComfyUI 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 a private AI media workbench to replace Nsketch AI. Requirements:

- A local web app on port 4317: Node.js 22, TypeScript, Fastify, React, and Vite.
  The server owns @fal-ai/client; the browser never receives the provider key.
- Implement exactly two workflows: text-to-image with fal-ai/nano-banana-2 and
  text-to-video with fal-ai/ltx-2.3/text-to-video/fast. Accept prompt and aspect ratio.
- Submit queued jobs server-side and save the provider request ID before polling.
  Resume unfinished jobs after restart; show queued, running, success, failed, and canceled.
- Store prompts, endpoints, parameters, state changes, cost estimates, errors, and local
  output paths in SQLite via better-sqlite3. Download files to media/YYYY-MM-DD/.
- The local page has a submission form and searchable gallery with compare, favorite,
  rerun, download, delete, and JSON metadata export actions.
- Read FAL_KEY from .env and ship .env.example. Validate inputs, use safe filenames,
  and show estimated per-job plus month-to-date API spend before a submission.
- Bind to localhost only. No accounts, billing, telemetry, or analytics; everything stays
  on my machine except prompts sent to fal.ai. Tests use a fake provider and spend nothing.
- Out of scope: the full model catalog, voice cloning, lip sync, motion transfer, social
  templates, hosted storage, public galleries, provider failover, and mobile apps.
- Include a README with setup, current endpoint costs, data and backup paths, provider
  safety policies, and a plain warning that every real generation spends money.

## Required capabilities

- Node.js 22
- fal.ai API key
- SQLite
- local media storage
- FFmpeg

## 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 Nsketch AI.

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 =====
# Nsketch AI indie build

## Goal

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

## Scope

Submit a prompt to one user-supplied media API, track the image or video job, review outputs in a private gallery, and export files with reproducible settings.

## 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:
- a broad, continuously updated catalog of image, video, voice, and motion models
- managed queues, concurrency, credits, retries, and provider failover
- hosted media storage, delivery, and cross-device asset history
- ready-made viral templates, editing utilities, and creator workflows
- production moderation, consent controls, support, and commercial operations

If those capabilities are essential, use ComfyUI 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 a private AI media workbench to replace Nsketch AI. Requirements:

- A local web app on port 4317: Node.js 22, TypeScript, Fastify, React, and Vite.
  The server owns @fal-ai/client; the browser never receives the provider key.
- Implement exactly two workflows: text-to-image with fal-ai/nano-banana-2 and
  text-to-video with fal-ai/ltx-2.3/text-to-video/fast. Accept prompt and aspect ratio.
- Submit queued jobs server-side and save the provider request ID before polling.
  Resume unfinished jobs after restart; show queued, running, success, failed, and canceled.
- Store prompts, endpoints, parameters, state changes, cost estimates, errors, and local
  output paths in SQLite via better-sqlite3. Download files to media/YYYY-MM-DD/.
- The local page has a submission form and searchable gallery with compare, favorite,
  rerun, download, delete, and JSON metadata export actions.
- Read FAL_KEY from .env and ship .env.example. Validate inputs, use safe filenames,
  and show estimated per-job plus month-to-date API spend before a submission.
- Bind to localhost only. No accounts, billing, telemetry, or analytics; everything stays
  on my machine except prompts sent to fal.ai. Tests use a fake provider and spend nothing.
- Out of scope: the full model catalog, voice cloning, lip sync, motion transfer, social
  templates, hosted storage, public galleries, provider failover, and mobile apps.
- Include a README with setup, current endpoint costs, data and backup paths, provider
  safety policies, and a plain warning that every real generation spends money.

## Required capabilities

- Node.js 22
- fal.ai API key
- SQLite
- local media storage
- FFmpeg

## 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 Nsketch AI.

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 =====
# Nsketch AI product brief

## Problem

The personal core is a focused prompt-to-media workbench over one or two user-supplied model APIs, and that is a credible weekend build. A true Nsketch AI replacement is not: the subscription bundles a fast-changing model catalog, credits, queues, media storage, templates, voice and motion workflows, safety, and failure recovery.

## Product outcome

Submit a prompt to one user-supplied media API, track the image or video job, review outputs in a private gallery, and export files with reproducible settings.

## Target user

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

## Required capabilities

- Node.js 22
- fal.ai API key
- SQLite
- local media storage
- FFmpeg

## Explicit non-goals for v1

- a broad, continuously updated catalog of image, video, voice, and motion models
- managed queues, concurrency, credits, retries, and provider failover
- hosted media storage, delivery, and cross-device asset history
- ready-made viral templates, editing utilities, and creator workflows
- production moderation, consent controls, support, and commercial operations

## 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 a private AI media workbench to replace Nsketch AI. Requirements:

- A local web app on port 4317: Node.js 22, TypeScript, Fastify, React, and Vite.
  The server owns @fal-ai/client; the browser never receives the provider key.
- Implement exactly two workflows: text-to-image with fal-ai/nano-banana-2 and
  text-to-video with fal-ai/ltx-2.3/text-to-video/fast. Accept prompt and aspect ratio.
- Submit queued jobs server-side and save the provider request ID before polling.
  Resume unfinished jobs after restart; show queued, running, success, failed, and canceled.
- Store prompts, endpoints, parameters, state changes, cost estimates, errors, and local
  output paths in SQLite via better-sqlite3. Download files to media/YYYY-MM-DD/.
- The local page has a submission form and searchable gallery with compare, favorite,
  rerun, download, delete, and JSON metadata export actions.
- Read FAL_KEY from .env and ship .env.example. Validate inputs, use safe filenames,
  and show estimated per-job plus month-to-date API spend before a submission.
- Bind to localhost only. No accounts, billing, telemetry, or analytics; everything stays
  on my machine except prompts sent to fal.ai. Tests use a fake provider and spend nothing.
- Out of scope: the full model catalog, voice cloning, lip sync, motion transfer, social
  templates, hosted storage, public galleries, provider failover, and mobile apps.
- Include a README with setup, current endpoint costs, data and backup paths, provider
  safety policies, and a plain warning that every real generation spends money.

## 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 Nsketch AI capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

# Nsketch AI indie build

## Goal

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

## Scope

Submit a prompt to one user-supplied media API, track the image or video job, review outputs in a private gallery, and export files with reproducible settings.

## 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:
- a broad, continuously updated catalog of image, video, voice, and motion models
- managed queues, concurrency, credits, retries, and provider failover
- hosted media storage, delivery, and cross-device asset history
- ready-made viral templates, editing utilities, and creator workflows
- production moderation, consent controls, support, and commercial operations

If those capabilities are essential, use ComfyUI 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 a private AI media workbench to replace Nsketch AI. Requirements:

- A local web app on port 4317: Node.js 22, TypeScript, Fastify, React, and Vite.
  The server owns @fal-ai/client; the browser never receives the provider key.
- Implement exactly two workflows: text-to-image with fal-ai/nano-banana-2 and
  text-to-video with fal-ai/ltx-2.3/text-to-video/fast. Accept prompt and aspect ratio.
- Submit queued jobs server-side and save the provider request ID before polling.
  Resume unfinished jobs after restart; show queued, running, success, failed, and canceled.
- Store prompts, endpoints, parameters, state changes, cost estimates, errors, and local
  output paths in SQLite via better-sqlite3. Download files to media/YYYY-MM-DD/.
- The local page has a submission form and searchable gallery with compare, favorite,
  rerun, download, delete, and JSON metadata export actions.
- Read FAL_KEY from .env and ship .env.example. Validate inputs, use safe filenames,
  and show estimated per-job plus month-to-date API spend before a submission.
- Bind to localhost only. No accounts, billing, telemetry, or analytics; everything stays
  on my machine except prompts sent to fal.ai. Tests use a fake provider and spend nothing.
- Out of scope: the full model catalog, voice cloning, lip sync, motion transfer, social
  templates, hosted storage, public galleries, provider failover, and mobile apps.
- Include a README with setup, current endpoint costs, data and backup paths, provider
  safety policies, and a plain warning that every real generation spends money.

## Required capabilities

- Node.js 22
- fal.ai API key
- SQLite
- local media storage
- FFmpeg

## 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.

# Nsketch AI product brief

## Problem

The personal core is a focused prompt-to-media workbench over one or two user-supplied model APIs, and that is a credible weekend build. A true Nsketch AI replacement is not: the subscription bundles a fast-changing model catalog, credits, queues, media storage, templates, voice and motion workflows, safety, and failure recovery.

## Product outcome

Submit a prompt to one user-supplied media API, track the image or video job, review outputs in a private gallery, and export files with reproducible settings.

## Target user

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

## Required capabilities

- Node.js 22
- fal.ai API key
- SQLite
- local media storage
- FFmpeg

## Explicit non-goals for v1

- a broad, continuously updated catalog of image, video, voice, and motion models
- managed queues, concurrency, credits, retries, and provider failover
- hosted media storage, delivery, and cross-device asset history
- ready-made viral templates, editing utilities, and creator workflows
- production moderation, consent controls, support, and commercial operations

## 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 a private AI media workbench to replace Nsketch AI. Requirements:

- A local web app on port 4317: Node.js 22, TypeScript, Fastify, React, and Vite.
  The server owns @fal-ai/client; the browser never receives the provider key.
- Implement exactly two workflows: text-to-image with fal-ai/nano-banana-2 and
  text-to-video with fal-ai/ltx-2.3/text-to-video/fast. Accept prompt and aspect ratio.
- Submit queued jobs server-side and save the provider request ID before polling.
  Resume unfinished jobs after restart; show queued, running, success, failed, and canceled.
- Store prompts, endpoints, parameters, state changes, cost estimates, errors, and local
  output paths in SQLite via better-sqlite3. Download files to media/YYYY-MM-DD/.
- The local page has a submission form and searchable gallery with compare, favorite,
  rerun, download, delete, and JSON metadata export actions.
- Read FAL_KEY from .env and ship .env.example. Validate inputs, use safe filenames,
  and show estimated per-job plus month-to-date API spend before a submission.
- Bind to localhost only. No accounts, billing, telemetry, or analytics; everything stays
  on my machine except prompts sent to fal.ai. Tests use a fake provider and spend nothing.
- Out of scope: the full model catalog, voice cloning, lip sync, motion transfer, social
  templates, hosted storage, public galleries, provider failover, and mobile apps.
- Include a README with setup, current endpoint costs, data and backup paths, provider
  safety policies, and a plain warning that every real generation spends money.

## 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 Nsketch AI 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