Cinestar is a free, open-source application for searching images and videos with local AI. It can ingest folders or videos, transcribe audio with Whisper, embed frames using BGE, and produce captions with Moondream. Natural-language searches return relevant moments with timecodes and thumbnails. Cinestar stores vectors in SQLite-Vec and uses Llama 3.2 to process and organize content. The maker says AI processing runs locally and the application has no analytics, telemetry, usage tracking, or data uploads. It is available for Linux and macOS under the MIT license. Local AI services require Ollama, and the installation guide lists BGE, Moondream, and Llama 3.2 downloads totaling about 2–4 GB. The site also describes plugins for tasks such as face recognition, metadata extraction, collaboration, backups, and multi-user access, plus an API for custom plugins. The maker presents it for personal media managers, content creators, media organizations, and academic or market researchers.
Who it is for
Cinestar may suit people managing personal media, creating content, or working with media collections in organizations or research. It is for users comfortable installing Ollama and downloading the listed AI models.
What is good
- Searches images and videos with natural-language queries.
- Results include timecodes and thumbnails.
- AI processing runs locally, according to the maker.
- Open source under the MIT license.
- Includes an API for custom plugins.
What to know first
- Local AI services require Ollama.
- Listed model downloads total about 2–4 GB.
- Available for Linux and macOS only.
Verdict
Cinestar combines local media indexing, transcription, captioning, and natural-language search in a free open-source application. Its local AI setup requires Ollama and the listed model downloads, so users should account for that installation requirement.
Cinestar plans and pricing
All plansCompared on AI video search tools
- Visual search
- Yes
- Audio search
- Yes
- Multimodal search
- Yes
