SharpAI/DeepCamera
DeepCamera
DeepCamera is an open-source AI video surveillance and network video recorder platform powered by local vision language models and hardware-accelerated processing. It integrates live feeds from network cameras, webcams, and mobile devices to monitor physical spaces while running local edge vision inference without relying on cloud servers.
The platform incorporates privacy-preserving video anonymization that converts raw video frames into abstract depth maps in real time, retaining motion tracking while protecting personal identity. Its modular architecture supports pluggable AI scripts and custom vision skills executed through an internal processing pipeline. An agentic event bus automatically dispatches intelligent security notifications and updates directly to external messaging services such as Telegram and Discord.
System management is handled through a desktop companion application that controls environment settings and interacts with the monitoring agents. Additionally, the platform includes performance evaluation suites for testing local vision models and security agents regarding scene understanding and threat resistance.
Features
- Vision-Language Models - Inspects live camera streams using vision-language models to monitor security threats.
- Security Agent Frameworks - Deploys autonomous security agents that watch property and interact with users through chat.
- Privacy Anonymization - Applies real-time video anonymization techniques to protect personal identity during surveillance.
- Hardware-Accelerated Inference - Executes vision language models locally on available hardware accelerators for efficient real-time video inference.
