Open Source Memory System for AI Glasses
aigclink · x · 2026-07-20
The ZJU Knowledge Graph group open-sourced LightMem-Ego, a first-person memory system for AI glasses: it streams camera and audio data for later retrieval and answering questions about finding things, recalling conversations, summarizing the day, discovering habits, etc.
The system divides continuous audio-visual experience into three layers: current memory, short-term memory, long-term memory. Queries are dynamically routed to the appropriate layer, and timestamped multimodal evidence is used to generate answers. The author emphasizes this is not a chatbot remembering chats, but a wearable memory middleware that captures what your eyes and ears see all day. Target scenarios include smart glasses, hands-free assistants, and a deployable personalized memory SDK.
Related event: Zhejiang University Open-Sources LightMem-Ego for AI Glasses(2 posts)→
More from Embodied
- Tesla expands Robotaxi rides to seven areas, including new Orlando and Tampa zones — elonmusk · 2026-07-22
- Hands-on robotics workshop on Saturday may be the last in-person session before August — StewartalsopIII · 2026-07-22
- NVIDIA pitches World Foundation Models as a way to scale physical AI data generation — MonaJalal_ · 2026-07-22
- RoboMME Podcast Preview: Benchmarking Memory for Robotic Policies — chris_j_paxton · 2026-07-21
- Gritt says an 8-person crew now installs 3,000 to 4,000 solar panels a day — HaktanSuren · 2026-07-21
- A helium-powered flying robot whale aims to be a quiet companion pet — chris_j_paxton · 2026-07-21