SharpAI/DeepCamera
Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your home via Telegram, Discord or Slack. Pluggable AI skills. OpenAI, Google, Anthropic or local AI. Runs on Mac Mini & AI PC. observed · 2026-08-28
Health v2 · maintenance only
86/100
- Activity 88
- Release rhythm 74
- Longevity 100
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: 23
- age_days: 2738
- days_rel: 173
- days_push: 76
- n_releases_24m: 2
Adoption not part of the score
3019 stars · 476 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
DeepCamera is an open-source AI camera skills platform that runs local VLM scene analysis, object detection, face recognition, and person re-identification on camera streams, with a pluggable skill architecture. Its companion desktop app, SharpAI Aegis, turns it into an LLM-powered security agent that watches, remembers, and answers questions about your home via Telegram, Discord, or Slack, using local models (Qwen, DeepSeek, SmolVLM, LLaVA, YOLO) or cloud AI.
Use cases
- analyze security camera footage with local vision language models
- detect people, cars, animals, and packages on my CCTV cameras
- build a privacy-first AI NVR without cloud subscriptions
- get plain-English answers about what happened at my front door
- send smart camera alerts to Telegram, Discord, or Slack
- run face recognition and person re-identification on a home camera system
- integrate AI camera detection with Home Assistant
- install pluggable AI skills on my security cameras
When to choose
- you want local, private AI video analysis on your own hardware (Mac Mini, AI PC)
- you need an agentic security camera system that answers natural-language questions about footage
- you want pluggable ML skills (detection, segmentation, depth) for cameras
- you prefer self-hosted NVR with LLM/VLM integration over cloud services
When to avoid
- you need an enterprise-grade video management system with certified compliance
- you have no capable local hardware and refuse cloud AI processing
- you only need simple motion detection without AI scene understanding
- you require multi-tenant commercial surveillance deployments
Facets
application · maturity active
computer-vision machine-learning object-storage chatbot agent-framework video-processing image-processing speech-recognition tts llm-inference computer-vision security privacy self-hosted artificial-intelligence windows self-hosted ai-camera nvr cctv vlm face-recognition object-detection home-assistant security-agent skill-marketplace local-ai telegram discord slack home-security macos linux desktop docker
3 sources
- readme: https://github.com/SharpAI/DeepCamera · fetched 2026-08-28 · bccad1b5e1cd
- homepage: http://www.sharpai.org · fetched 2026-08-29 · 34280c8f5fe0
- site_page: https://docs.sharpai.org · fetched 2026-08-29 · 79e4614e7b0a
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| SharpAI/DeepCamera | main | 86 |
For agents
markdown · JSON · MCP: product_card(name="SharpAI/DeepCamera")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem