Skip to content
SPECIFICTION
Get listed

Cinestar

cinestar.sourceforge.io

Free plan Open source WindowsmacOSLinuxAPISelf-hosted
Visit cinestar.sourceforge.io
Spec score 9.1 #2 of 24 in AI Video Search Tools

What it is

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.

Spec sheet

What it does
Cinestar is a desktop application for natural-language searching across images, videos, and audio files with local AI.Read 20 Oct 2026 · github.com
Purpose
Cinestar searches images and videos using local AI.Read 4 Oct 2026 · cinestar.sourceforge.io
Intended users
The maker presents personal media managers, content creators, media organizations, and academic or market researchers as use cases.Read 4 Oct 2026 · cinestar.sourceforge.io
API
Cinestar’s site advertises an open API for creating custom plugins.Read 20 Oct 2026 · cinestar.sourceforge.io
Integrations
Listed plugin possibilities include Google Photos-style face recognition, social sharing, LDAP, audit trails, backups, compliance reporting, and multi-user access control.Read 20 Oct 2026 · cinestar.sourceforge.io
Privacy
The maker states that inference, media, and search queries stay local without cloud uploads.Read 20 Oct 2026 · cinestar.sourceforge.io
License
The site identifies Cinestar as open source under the MIT license.Read 4 Oct 2026 · cinestar.sourceforge.io
AI dependency
The install guide requires Ollama and lists roughly 2–4 GB of model downloads.Read 20 Oct 2026 · cinestar.sourceforge.io
Audio processing
Audio files are transcribed and analyzed for searchable content.Read 20 Oct 2026 · github.com
Changelog
Version 0.1.52, dated October 11, 2025, unified configuration files and fixed Whisper model downloading in packaged builds.Read 20 Oct 2026 · cinestar.sourceforge.io
Developer setup
Building from source requires Node.js 18 or newer, npm, and the commands npm install followed by npm run dev or npm run build.Read 20 Oct 2026 · cinestar.sourceforge.io
Docker deployment
The documentation supplies Docker Compose configurations for Ollama and Whisper services, including optional multi-GPU load balancing.Read 20 Oct 2026 · cinestar.sourceforge.io
Documentation depth
The install page includes health checks, Ollama API testing, service ports, memory reservations, and Nginx routing examples.Read 20 Oct 2026 · cinestar.sourceforge.io
Downloads
The v0.1.64 directory contains Linux ARM64, Linux x86_64, and macOS installers dated November 5, 2025.Read 20 Oct 2026 · sourceforge.net
GitHub activity
The public release repository shows 1 star, 1 fork, and zero listed issues or pull requests.Read 20 Oct 2026 · github.com
Image recognition
Images receive AI-generated captions that can be searched.Read 20 Oct 2026 · github.com
Independent architecture detail
The independent report says Cinestar combines 70% vector similarity from sqlite-vec with 30% SQLite FTS5 scoring.Read 20 Oct 2026 · ikouchiha47.github.io
Independent performance detail
That write-up reports approximately 40 seconds to make a 60-minute video searchable during its initial audio phase.Read 20 Oct 2026 · ikouchiha47.github.io
Independent technical report
An independent engineering write-up describes a five-phase pipeline that makes video segments searchable after local Whisper transcription and later enriches them with visual captions.Read 20 Oct 2026 · ikouchiha47.github.io
Indexing
Vectors are stored in SQLite-Vec and organized with Llama 3.2.Read 20 Oct 2026 · cinestar.sourceforge.io
Installation
The install guide instructs macOS users to copy Cinestar.app into Applications and clear Gatekeeper quarantine when necessary.Read 20 Oct 2026 · cinestar.sourceforge.io
Licence
Cinestar is presented as open source under the MIT licence.Read 20 Oct 2026 · sourceforge.net
Limit: hardware demand
The independent report estimates about 4 GB memory with all models loaded and about 500 MB of disk per hour of video.Read 20 Oct 2026 · ikouchiha47.github.io
Limit: project maturity
SourceForge labels Cinestar Alpha, shows zero weekly downloads on the project summary, and says users should be the first to post a review.Read 20 Oct 2026 · sourceforge.net
Linux install
The install guide includes Linux commands for installing Ollama and names Linux in the site's Mac/Linux install link.Read 4 Oct 2026 · cinestar.sourceforge.io
Local processing
The project says AI processing runs on the user’s own machine for privacy.Read 20 Oct 2026 · github.com
macOS install
The install guide provides steps for downloading Cinestar.app, moving it to Applications, and opening it past Gatekeeper.Read 4 Oct 2026 · cinestar.sourceforge.io
Media ingestion
It can ingest folders or videos, transcribe audio with Whisper, embed frames with BGE, and generate captions with Moondream.Read 4 Oct 2026 · cinestar.sourceforge.io
Models
The product uses BGE-large embeddings, Moondream v2 vision, Llama 3.2 3B, and Whisper transcription.Read 20 Oct 2026 · cinestar.sourceforge.io
Notable news
The GitHub repository records release v0.1.53 on October 11, 2025.Read 20 Oct 2026 · github.com
Plugin system
The official site describes consumer, professional, and enterprise plugin categories.Read 20 Oct 2026 · cinestar.sourceforge.io
Plugins and API
The site describes plugins for face recognition, album creation, metadata extraction, transcoding, collaboration, LDAP, audit trails, backups, compliance reporting, and multi-user access, plus an open API for custom plugins.Read 4 Oct 2026 · cinestar.sourceforge.io
Rating on SourceForge
No rating shown from 0 user reviews.Read 20 Oct 2026 · sourceforge.net
Release information
The changelog lists v0.1.52, dated October 11, 2025, as the latest release on that page.Read 4 Oct 2026 · cinestar.sourceforge.io
Search results
Natural-language searches return matching moments with timecodes and thumbnails.Read 20 Oct 2026 · cinestar.sourceforge.io
Semantic search
The application supports semantic media search from natural-language descriptions.Read 20 Oct 2026 · github.com
Setup requirement
The install guide says Ollama is required for local AI services and lists BGE, Moondream, and Llama 3.2 models totaling about 2–4 GB to download.Read 4 Oct 2026 · cinestar.sourceforge.io
SourceForge metadata
SourceForge lists Electron as the interface, JavaScript as the programming language, and SQLite as the database environment.Read 20 Oct 2026 · sourceforge.net
SourceForge status
SourceForge classifies the project as Alpha and identifies the account itador1sensei as its maintainer.Read 20 Oct 2026 · sourceforge.net
Telemetry
The maker claims there are no analytics, telemetry, or usage tracking.Read 20 Oct 2026 · cinestar.sourceforge.io
Video analysis
Cinestar transcribes videos and performs scene understanding automatically.Read 20 Oct 2026 · github.com
Windows build
The public GitHub README names a Windows executable alongside macOS and Linux builds for version 0.1.53.Read 20 Oct 2026 · github.com

Plans and prices

Cinestar (MIT open-source core) Free Open-source core; local AI services require Ollama Read 4 Oct 2026 · cinestar.sourceforge.io

Every Cinestar plan and price →

Strong points and limits

Strong points

  • Natural-language searches return moments with timecodes and thumbnails.
  • AI processing runs locally, according to the maker.
  • The MIT-licensed core is listed at free.
  • An open API supports custom plugins.
  • Available for Linux and macOS.

Limits

  • Local AI services require Ollama.
  • Listed model downloads total about 2–4 GB.
  • The latest release listed is v0.1.52, dated October 11, 2025.

Who it suits

It may suit personal media managers, content creators, media organizations, and academic or market researchers who want local AI search for image and video collections. Users need Ollama and the listed model downloads for local AI services.

Verdict

Cinestar combines media ingestion, transcription, captions, and searchable moments, with AI processing described as local. Setup requires Ollama and model downloads, so account for those requirements before choosing it.

Where Specifiction places it

Alternatives to CinestarAll alternatives →