LightMem-Ego: Everyday AI Memory
zjunlp · hf · 2026-07-14
LightMem-Ego is a lightweight streaming multimodal memory system for daily life assistants. It aims to continuously record users' visual and audio streams on smartphones and wearables while answering questions about past experiences.
The system does three things:
- Continuously captures egocentric visual/audio streams and aligns them to a unified timeline.
- Organizes memory into a hierarchical structure: current memory, short-term memory, and long-term memory.
- Dynamically routes queries to the appropriate memory layer and generates answers based on multimodal evidence.
The authors state the demo can be deployed on smartphones and AI glasses, supporting object finding, conversation recall, life summarization, daily routine discovery, and personalized assistance. Code is open-sourced on GitHub: zjunlp/LightMem-Ego.
More from Embodied
- UniAction: unified action conditioning lets one world model handle mixed action types — ZeYanjie · 2026-10-27
- StackChan robot performs an AI-generated skit, orchestrated by Hermes Agent via JSON script — alexcovo_eth · 2026-10-27
- DONIC hits 86.79% on bimanual dexterous tracking, crushing prior SOTA's 9.43% — liuziwei7 · 2026-10-27
- Bedrock Robotics raises $600M as its fully autonomous excavators do paid work on live job sites — Sethwinterroth · 2026-10-27
- AW-0 hits 80.8% on RoboTwin tasks, beating strongest baseline by 16 points — trevordarrell · 2026-10-27
- AW-0's code stream fixes world model prediction: picks mango where baseline grabs apple — trevordarrell · 2026-10-27