Cinestar vs Vivu
Cinestar
cinestar.sourceforge.ioVivu
vivu.aiSide by side
| Figure | Cinestar | Vivu |
|---|---|---|
| Price from | Free | $30/mo |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | Yes | — |
| Web | — | Yes |
| Windows | Yes | — |
| macOS | Yes | — |
| Linux | Yes | — |
| API | Yes | Yes |
| Self-hosted | Yes | — |
| Plans published | 1 | 2 |
| Spec score · AI Video Search Tools | 9.1 (#2) | 7.6 (#17) |
| Integrations | Listed plugin possibilities include Google Photos-style face recognition, social sharing, LDAP, audit trails, backups, compliance reporting, and multi-user access control. | Claude is the main connector setup, and the maker says other MCP clients can connect to the same server. |
| Intended users | The maker presents personal media managers, content creators, media organizations, and academic or market researchers as use cases. | Vivu describes workflows for marketing, sales and enablement, training, events, AI and product teams, robotics, and customer support. |
| Purpose | Cinestar searches images and videos using local AI. | Vivu makes video libraries searchable by meaning and returns candidate moments as time ranges. |
Plans
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.
Vivu
Vivu makes video libraries searchable by meaning, returning candidate moments as time ranges. It indexes each uploaded video in its cloud across speech, visuals, speakers, on-screen text, and timing. Fast search uses one credit; Precise search adds a refinement pass, for five credits total. Searches run within a single project, and Vivu does not edit or generate video. The web app and remote MCP server support Claude and other MCP clients, including ChatGPT, over Streamable HTTP with OAuth. The connector documentation says browser uploads accept common video formats. Footage stays private to the customer's workspace, and users must sign in to access projects and searches. Uploaded videos and derived data remain in the account until the video or project is deleted; deletion is permanent. Vivu says data travels over HTTPS and sign-in uses Google Firebase Authentication, while its product backend runs in Google Cloud's us-central1 region in the United States. The Free plan is free and includes 20 indexing minutes and 50 search credits monthly. Premium is $30 a month, with 180 indexing minutes and 500 search credits monthly.