SentrySearch
SentrySearch is an open-source tool for finding moments in video footage with text or reference images, then returning trimmed clips.
What SentrySearch is
SentrySearch is an open-source tool for finding moments in video footage with text or reference images, then returning trimmed clips. It scans folders recursively for MP4 and MOV files, including footage unrelated to Tesla Sentry Mode. Videos are divided into overlapping chunks and embedded with queries in a shared vector space; video vectors are kept in a local ChromaDB database. Search options include text, image, anomaly highlights, and optional reranking. Available embedding backends include Gemini, Alibaba DashScope Qwen Cloud, LiteLLM, local Qwen3-VL, and MLX for Apple Silicon. The local backend runs on the user's machine without an API key and is described as private and offline-capable. With Qwen Cloud, the official SDK uploads local video chunks to temporary DashScope-managed storage for processing. Optional Tesla footage support can surface speed, GPS, and time metadata, with location labels through optional OpenStreetMap reverse geocoding. Requirements include Python 3.11 or later and FFmpeg or imageio-ffmpeg. Local inference requires CUDA or Apple Metal; macOS video decoding requires system FFmpeg. Still-frame detection may miss subtle motion, and events across chunk boundaries may not match perfectly.
Good
- Search by text or reference image.
- Scans MP4 and MOV files recursively.
- Local backend needs no API key.
- Apache-2.0 licensed and free.
Watch out
- Requires Python 3.11 or later.
- Local inference requires CUDA or Apple Metal.
- Still-frame detection can miss subtle motion.
- Chunk-boundary events may not match perfectly.
Who it suits
SentrySearch suits people who want to search video archives by text or image and extract matching clips. It may also suit Tesla footage users who want supported driving metadata displayed.
Verdict
SentrySearch combines semantic video search with clip trimming and anomaly highlights. Choose its local backend for on-machine processing, or note that Qwen Cloud uploads chunks to temporary managed storage.
The facts
Each one read from SentrySearch's own pages, with the date it was checked.
What it does
- Cloud data handling
- For the Qwen Cloud backend, local video chunk files are uploaded to DashScope-managed temporary object storage before API processing.checked 8 Oct 2026
- Compatibility
- The directory scanner recursively finds MP4 and MOV footage, including footage not recorded in Tesla Sentry Mode.checked 8 Oct 2026
- Embedding backends
- It supports Gemini Embedding, Alibaba DashScope Qwen Cloud, LiteLLM gateways, and local Qwen3-VL models.checked 8 Oct 2026
- Highlights
- The highlights command ranks anomalous clips in an index and can trim them automatically.checked 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.checked 7 Oct 2026
- Integrations
- SentrySearch can hand search results to the maker's SentryMerge tool and saved clips to SentryBlur.checked 8 Oct 2026
- License
- The GitHub repository identifies the project as Apache-2.0 licensed.checked 8 Oct 2026
- Limits
- Still-frame detection is heuristic, and search quality can be affected when an event crosses chunk boundaries.checked 8 Oct 2026
- Local processing
- The local backend runs without an API key and processes footage on the user's machine.checked 8 Oct 2026
- Privacy
- The README describes the local backend as private and says it runs entirely on the user's machine.checked 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.checked 7 Oct 2026
- Purpose
- SentrySearch performs semantic search over video footage and returns trimmed clips.checked 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.checked 8 Oct 2026
- Search methods
- Users can search with text queries or reference images.checked 8 Oct 2026
- Search modes
- It supports text search, image search, anomaly highlights, and optional reranking of candidate clips.checked 7 Oct 2026
- Supported footage
- The directory scanner recursively finds MP4 and MOV files, including footage that is not from Tesla Sentry Mode.checked 7 Oct 2026
- Tesla overlay
- An optional overlay can display Tesla dashcam speed, date, time, city, and road name when supported metadata is available.checked 8 Oct 2026
- Tesla support
- An optional overlay extracts speed, GPS, and time metadata from supported Tesla driving footage and can add location labels through optional OpenStreetMap reverse geocoding.checked 7 Oct 2026
- Video handling
- It splits videos into overlapping chunks, stores embeddings in a local ChromaDB database, and can trim matching clips.checked 8 Oct 2026
The company
- Maker
- The maintainer's GitHub profile names Soham Rajadhyaksha and lists Fremont, California.checked 8 Oct 2026
Money
- Usage costs
- The README estimates Gemini indexing at about $2.84 per hour of footage with its default settings and says local-backend calls use no API quota.checked 7 Oct 2026
Alternatives to SentrySearch
- 1
Deepgrip
Free planWebAPILinuxmacOS7.7From $89 a month - 2
FrameQuery
Free planWebAPImacOSWindows7.7From $19 a month - 3
VGG Image Annotator
Free planOpen sourceWebLinuxmacOSSelf-hosted7.7Free plan - 4
DISKO
Free planWebmacOS7.4From $12 a month - 5
Twelve Labs
Free planWebAPI7.3From $29 a month - 6
ViSearch
Free planWebAPIExtensionSelf-hosted7.3$0.09 one-time