Skip to content
SPECIFICTION
Get listed

Danbi vs SentrySearch

Danbi

danbi.ai

SentrySearch

github.com

Side by side

FigureDanbiSentrySearch
Price from——
Free plan——
Free trialYes—
Open source——
Windows—Yes
macOS—Yes
Linux—Yes
APIYes—
Self-hosted—Yes
Plans published30
Spec score · AI Video Search Tools8.3 (#9)7.2 (#20)
PurposeDanbi indexes video archives so teams can search for moments in plain English and AI agents can query them through MCP.SentrySearch performs semantic search over video footage and returns trimmed clips.

Plans

Danbi

  • Free recording trialFree
  • Danbi archive indexingPriced on request
  • Prepaid recording hoursPriced on request

Danbi pricing →

SentrySearch

No plans published.

SentrySearch pricing →

In their own words

Danbi

Danbi is an API for indexing video archives so teams can search for moments in plain English and AI agents can query the archive through MCP. Its index can structure faces, spoken words, actions, objects, on-screen text, and timecodes. Searches return exact moments that can be played, cited, exported, or shared, with subtitles and retention listed for the archive product. Danbi can run beside a media asset management system: that system supports human catalog browsing while Danbi handles AI-assisted retrieval and agents. Deployment uses the customer’s own hardware and infrastructure by default, and indexed results remain on infrastructure the customer controls. Selected fragments that benefit from third-party models may be sent out. The free recording trial processes files on Danbi’s hardware, accepts recordings up to 90 minutes and 2 GB, and deletes them two hours after they are ready. Danbi offers visual, audio, and multimodal search.

Visit danbi.ai

SentrySearch

SentrySearch searches video footage by text or reference image and can return trimmed matching clips. It splits videos into overlapping chunks, embeds footage and queries into a shared vector space, and stores video vectors in a local ChromaDB database. Search options include text, image, anomaly highlights, and optional reranking of candidate clips. The project documents embedding backends including Gemini, Alibaba DashScope Qwen Cloud, LiteLLM, local Qwen3-VL, and MLX for Apple Silicon. Its local backend runs on the user's machine without an API key and is described as private and offline-capable. With Qwen Cloud, local video chunks are uploaded by the official SDK to DashScope-managed temporary object storage for processing. The scanner recursively finds MP4 and MOV files, including footage not from Tesla Sentry Mode. An optional Tesla overlay can use supported footage metadata for speed, GPS, and time information. The project requires Python 3.11 or later and FFmpeg or imageio-ffmpeg. It is open source under Apache-2.0 and supports Linux, macOS, Windows, and self-hosting.

Visit github.com