Can Shade be vibe coded?
AI-indexed asset manager for creative teams: search footage by face, transcript, scene description, or a full sentence
The search half is real and rebuildable. Extract keyframes with ffmpeg, embed them with CLIP, transcribe the audio with whisper, put the vectors in SQLite, and 'the drone shot over the bridge at golden hour' finds the clip on your own drives. The open-source stack for that is mature and the result is genuinely good. What does not survive the port is what Shade has grown into: cloud streaming so an editor opens full-res without waiting on a download, per-link permissions and guest access, review and approval, and a model pipeline that keeps improving without you retraining anything. Solo, on local storage, the DIY version wins outright. On a team, you are rebuilding a platform and calling it a script.
Jump to the build brief ↓Checked Jul 2026
What you pay today, before any DIY hosting
medium editorial confidence
Buildability by layer
Screens, forms, and focused interactions
The repeatable job the product performs
Availability and legality of required data
Uptime, queues, support, and maintenance
Security, compliance, and user confidence
The achievable core
- Walk my drives, pull keyframes and transcripts, embed both with CLIP and whisper into a local vector index, then search the whole library in plain English.
- Build a focused single-user workflow with real persistence, search, and export.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- cloud streaming of full-res files without downloading them first
- guest links with per-link permissions and roles
- built-in review, approval, and commenting
- face recognition and shot-type tagging that improves without your involvement
- Permissions, presence, and shared workflows are difficult to simplify.
- Reliability at the vendor's scale is an operations problem, not a prompt.
Why people still pay
They pay because the search only matters if the whole team gets it. A local index that only lives on the editor's machine solves the editor's problem and nobody else's, and the person who most needs to find the clip is usually the one furthest from the storage. Shade sells the index plus the delivery of what the index found, and the second half is the expensive one.
Permissions, presence, and shared workflows are difficult to simplify.
Reliability at the vendor's scale is an operations problem, not a prompt.
Model quality and inference operations are part of the product.
The brief
Context, requirements, acceptance criteria, non-goals, and the full production standard — as Markdown, ready for any coding agent.
Build brief — a focused alternative to Shade
Context
**Shade** — AI-indexed asset manager for creative teams: search footage by face, transcript, scene description, or a full sentence. It currently costs $35/mo.
The search half is real and rebuildable. Extract keyframes with ffmpeg, embed them with CLIP, transcribe the audio with whisper, put the vectors in SQLite, and 'the drone shot over the bridge at golden hour' finds the clip on your own drives. The open-source stack for that is mature and the result is genuinely good. What does not survive the port is what Shade has grown into: cloud streaming so an editor opens full-res without waiting on a download, per-link permissions and guest access, review and approval, and a model pipeline that keeps improving without you retraining anything. Solo, on local storage, the DIY version wins outright. On a team, you are rebuilding a platform and calling it a script.
This brief describes a focused, single-operator replacement for the part of Shade that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.
What you are building
Walk my drives, pull keyframes and transcripts, embed both with CLIP and whisper into a local vector index, then search the whole library in plain English.
Build a focused single-user workflow with real persistence, search, and export.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
Ffmpeg.
A CLIP model via transformers.js or Python.
Whisper.cpp.
Sqlite-vec or another local vector store.
A GPU, or patience measured in nights.
Non-functional
Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
Security: server-side secrets, validated input, and no credentials in the client bundle.
Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
Portability: the operator can export their data and leave without losing it.
Implementation brief
Build me a semantic search engine for my own footage to replace Shade. Requirements:
A Python CLI plus a small FastAPI web UI on localhost. SQLite with sqlite-vec for
the vectors and the metadata, one file at ~/FootageIndex/index.db.
`index <folder>` walks the tree, and for every video ffmpeg pulls a keyframe every
5 seconds plus one at each scene cut detected by the ffmpeg scene filter.
Each keyframe is embedded with open_clip (ViT-B/32) and stored with its timestamp.
Stills and photos get the same treatment as a single frame.
Audio goes through whisper.cpp for a transcript with word timestamps, chunked into
30-second windows and embedded with sentence-transformers for text search.
The search box takes a plain sentence and searches image and transcript vectors
together, returning ranked results as thumbnail, filename, and timecode. Clicking
one opens the clip at that exact frame in a player.
Indexing is incremental and resumable, keyed on file path plus mtime plus size, and
prints a running count so an overnight run is checkable in the morning.
Everything runs on my machine, models included · no accounts, no cloud, no
telemetry, no API keys. Files are read only, never moved or renamed.
Out of scope: face recognition, sharing links, review and comments, and team sync.
Do not build auth or a server deployment, this is a single-user local tool.
README: installing ffmpeg and whisper.cpp, first-run model downloads, an honest
estimate of indexing hours per TB on CPU versus GPU, and how to reset the index.
Delivery standard
Inspect the repository first, then write a short implementation plan before writing code.
Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
Add structured logs around every external call and return actionable errors without leaking sensitive details.
Write unit tests for the core logic and one automated test of the main user journey.
Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.
Acceptance criteria
A clean install starts the app using only the README and .env.example.
The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
Tests, type checking, linting, and a production build all pass with no ignored failures.
No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.
Non-goals
Do not build these, and do not claim to have replaced them:
Cloud streaming of full-res files without downloading them first.
Guest links with per-link permissions and roles.
Built-in review, approval, and commenting.
Face recognition and shot-type tagging that improves without your involvement.
Permissions, presence, and shared workflows are difficult to simplify.
Reliability at the vendor's scale is an operations problem, not a prompt.
What you still own after launch
Run migrations, backups, restores, and dependency updates.
Test the critical journey after every model, API, or hosting change.
Monitor failures and fix the edge cases a first prompt will miss.
Risk
**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.
Editorial confidence in this assessment: medium. No independent one-shot implementation is linked yet.
Prior art
Working open-source software you can read, fork, or borrow from before starting:
[Immich](https://github.com/immich-app/immich) — Self-hosted photo and video library with CLIP semantic search and face recognition already built in. The closest working proof the search half is solved
[PhotoPrism](https://github.com/photoprism/photoprism) — Self-hosted AI-tagged media library with local indexing and search. Photo-first, but the same pattern
Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/shade
You still own the product
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
Open-source prior art
Before you start
Can Shade be vibe coded?
Partly, if you narrow it. The search half is real and rebuildable. Extract keyframes with ffmpeg, embed them with CLIP, transcribe the audio with whisper, put the vectors in SQLite, and 'the drone shot over the bridge at golden hour' finds the clip on your own drives. The open-source stack for that is mature and the result is genuinely good. What does not survive the port is what Shade has grown into: cloud streaming so an editor opens full-res without waiting on a download, per-link permissions and guest access, review and approval, and a model pipeline that keeps improving without you retraining anything. Solo, on local storage, the DIY version wins outright. On a team, you are rebuilding a platform and calling it a script.
What can an AI coding agent reproduce from Shade?
Walk my drives, pull keyframes and transcripts, embed both with CLIP and whisper into a local vector index, then search the whole library in plain English. Build a focused single-user workflow with real persistence, search, and export. A responsive interface with real empty, loading, success, and error states.
What will a DIY Shade replacement still be missing?
cloud streaming of full-res files without downloading them first; guest links with per-link permissions and roles; built-in review, approval, and commenting; face recognition and shot-type tagging that improves without your involvement; Permissions, presence, and shared workflows are difficult to simplify.; Reliability at the vendor's scale is an operations problem, not a prompt.
What do I still own after building a Shade alternative?
Run migrations, backups, restores, and dependency updates. Test the critical journey after every model, API, or hosting change. Monitor failures and fix the edge cases a first prompt will miss.