- Home
- AI Video Search Tools
- SentrySearch
SentrySearch
What it is
SentrySearch is an open-source tool for finding moments in video footage and producing trimmed clips that match a search. It recursively scans for MP4 and MOV files, whether or not they come from Tesla Sentry Mode. The tool divides footage into overlapping chunks, embeds them alongside text or image queries in a shared vector space, and stores video vectors in a local ChromaDB database. Search options include text, reference images, anomaly highlights, and optional reranking of candidate clips. Embedding backends include 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. Qwen Cloud processing involves the official SDK uploading local chunks to DashScope-managed temporary storage. Optional Tesla support can extract driving metadata and show an overlay. The project requires Python 3.11 or later and FFmpeg or imageio-ffmpeg; local inference also requires CUDA or Apple Metal. Gemini indexing is estimated at about $2.84 per hour of footage using default settings.
For and against
For
- Searches with text or reference images.
- Finds MP4 and MOV files recursively.
- Local backend runs without an API key.
- Supports anomaly highlights and clip trimming.
- Apache-2.0 licensed open-source repository.
Against
- Requires Python 3.11 or later and FFmpeg.
- Local inference requires CUDA or Apple Metal.
- Qwen Cloud uploads chunks to temporary storage.
- Still-frame detection can miss subtle motion.
The verdict
SentrySearch offers several search backends and can trim matching footage, with local processing available as an option. Be aware of its installation requirements, imperfect detection across subtle motion or chunk boundaries, and the data handling used by Qwen Cloud.
Who it suits
SentrySearch may suit people who need to find scenes in local video collections using text or images. Its local backend is an option for users who want processing on their own machine without an API key.
On the record
- Cloud data handling
- For the Qwen Cloud backend, local video chunk files are uploaded to DashScope-managed temporary object storage before API processing.github.com · read 8 Oct 2026
- Compatibility
- The directory scanner recursively finds MP4 and MOV footage, including footage not recorded in Tesla Sentry Mode.github.com · read 8 Oct 2026
- Embedding backends
- It supports Gemini Embedding, Alibaba DashScope Qwen Cloud, LiteLLM gateways, and local Qwen3-VL models.github.com · read 8 Oct 2026
- Highlights
- The highlights command ranks anomalous clips in an index and can trim them automatically.github.com · read 8 Oct 2026
- How it works
- It embeds video chunks and text or image queries into a shared vector space, stores video vectors in a local ChromaDB database, and matches queries against them.github.com · read 7 Oct 2026
- Integrations
- SentrySearch can hand search results to the maker's SentryMerge tool and saved clips to SentryBlur.github.com · read 8 Oct 2026
- License
- The GitHub repository identifies the project as Apache-2.0 licensed.github.com · read 8 Oct 2026
- Limits
- Still-frame detection is heuristic, and search quality can be affected when an event crosses chunk boundaries.github.com · read 8 Oct 2026
- Local processing
- The local backend runs without an API key and processes footage on the user's machine.github.com · read 8 Oct 2026
- Maker
- The maintainer's GitHub profile names Soham Rajadhyaksha and lists Fremont, California.github.com · read 8 Oct 2026
- Privacy
- The README describes the local backend as private and says it runs entirely on the user's machine.github.com · read 8 Oct 2026
- Privacy option
- The local backend runs on the user's machine without an API key, which the README describes as private and offline-capable.github.com · read 7 Oct 2026
- Purpose
- SentrySearch performs semantic search over video footage and returns trimmed clips.github.com · read 8 Oct 2026
- Requirements
- The project requires Python 3.11 or later and FFmpeg, with bundled FFmpeg available through imageio-ffmpeg for the default setup.github.com · read 8 Oct 2026
- Search methods
- Users can search with text queries or reference images.github.com · read 8 Oct 2026
- Search modes
- It supports text search, image search, anomaly highlights, and optional reranking of candidate clips.github.com · read 7 Oct 2026
- Supported footage
- The directory scanner recursively finds MP4 and MOV files, including footage that is not from Tesla Sentry Mode.github.com · read 7 Oct 2026
- Tesla overlay
- An optional overlay can display Tesla dashcam speed, date, time, city, and road name when supported metadata is available.github.com · read 8 Oct 2026
