Cinestar vs FrameQuery
Cinestar
cinestar.sourceforge.ioFrameQuery
framequery.comSide by side
| Figure | Cinestar | FrameQuery |
|---|---|---|
| Price from | Free | $19/mo |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | Yes | — |
| Web | — | Yes |
| Windows | Yes | Yes |
| macOS | Yes | Yes |
| Linux | Yes | — |
| API | Yes | Yes |
| Self-hosted | Yes | — |
| Plans published | 1 | 6 |
| Spec score · AI Video Search Tools | 9.1 (#2) | 9.1 (#3) |
| Licence | Cinestar is presented as open source under the MIT licence. | The EULA describes proprietary desktop software under a limited, non-exclusive licence and prohibits reverse engineering and redistribution. |
| What it does | Cinestar is a desktop application for natural-language searching across images, videos, and audio files with local AI. | FrameQuery indexes video so users can search dialogue, on-screen content, people and scene context locally. |
Plans
FrameQuery
- FreeFree
- Starter$19 a month
- Pro$45 a month
- Max$190 a month
- Developer APIPriced on request
- StudioPriced on request
In their own words
Cinestar
Cinestar is an open-source application for searching images and videos with locally run AI services. It can ingest folders or videos, transcribe audio with Whisper, embed frames with BGE, and create captions with Moondream. Natural-language searches return matching moments with timecodes and thumbnails. Cinestar stores vectors in SQLite-Vec and uses Llama 3.2 for language tasks and content organization. The maker says it has no analytics, telemetry, usage tracking, or data uploads. It is available for Linux and macOS under the MIT license, and the listed open-source core costs nothing. Local AI services require Ollama; the install guide lists BGE, Moondream, and Llama 3.2 model downloads totaling about 2–4 GB. The site describes plugins for functions including face recognition, metadata extraction, collaboration, backups, and multi-user access, plus an open API for custom plugins. The maker presents it for personal media managers, content creators, media organizations, and academic or market researchers. Its changelog lists v0.1.52, dated October 11, 2025, as the latest release on that page.
FrameQuery
FrameQuery makes video footage searchable by dialogue, on-screen content and people. Indexing identifies scene context, objects, faces, voices and speech, with transcripts separated by speaker; after indexing, searches run locally and work offline without a per-query charge. It supports more than 50 formats, including R3D, BRAW, ProRes, H.264, H.265, MKV and MXF. Sources include local folders, S3, SMB, Dropbox and Google Drive, while sharing or backup can use Drive, Dropbox or NAS. Search results can be exported to editing workflows such as Final Cut Pro, Premiere Pro, DaVinci Resolve and Avid using formats including FCPXML, Premiere XML, EDL and LosslessCut. A web review page offers frame-accurate comments, drawing annotations, approvals and side-by-side version comparison. Face and voice recognition run on-device with explicit consent, but selected frames and extracted audio go to cloud services for analysis and transcription. The Free plan has no monthly indexing hours. Starter costs $19 a month and includes 10 hours of video per month. Its API is planned but not available yet.